From f99952d485891d83e1355364a1f18955086e35b6 Mon Sep 17 00:00:00 2001
From: John Grimes <John.Grimes@csiro.au>
Date: Fri, 29 May 2026 04:29:59 +1000
Subject: [PATCH 1/6] Initialise OpenSpec

---
 .claude/CLAUDE.md                             |  59 ++
 .claude/commands/opsx/apply.md                | 152 +++++
 .claude/commands/opsx/archive.md              | 157 +++++
 .claude/commands/opsx/bulk-archive.md         | 242 ++++++++
 .claude/commands/opsx/continue.md             | 114 ++++
 .claude/commands/opsx/explore.md              | 173 ++++++
 .claude/commands/opsx/ff.md                   |  97 +++
 .claude/commands/opsx/new.md                  |  69 +++
 .claude/commands/opsx/onboard.md              | 550 +++++++++++++++++
 .claude/commands/opsx/sync.md                 | 134 +++++
 .claude/commands/opsx/verify.md               | 164 ++++++
 .claude/skills/openspec-apply-change/SKILL.md | 156 +++++
 .../skills/openspec-archive-change/SKILL.md   | 114 ++++
 .../openspec-bulk-archive-change/SKILL.md     | 246 ++++++++
 .../skills/openspec-continue-change/SKILL.md  | 118 ++++
 .claude/skills/openspec-explore/SKILL.md      | 288 +++++++++
 .claude/skills/openspec-ff-change/SKILL.md    | 101 ++++
 .claude/skills/openspec-new-change/SKILL.md   |  74 +++
 .claude/skills/openspec-onboard/SKILL.md      | 554 ++++++++++++++++++
 .claude/skills/openspec-sync-specs/SKILL.md   | 138 +++++
 .../skills/openspec-verify-change/SKILL.md    | 168 ++++++
 openspec/config.yaml                          |  20 +
 22 files changed, 3888 insertions(+)
 create mode 100644 .claude/CLAUDE.md
 create mode 100644 .claude/commands/opsx/apply.md
 create mode 100644 .claude/commands/opsx/archive.md
 create mode 100644 .claude/commands/opsx/bulk-archive.md
 create mode 100644 .claude/commands/opsx/continue.md
 create mode 100644 .claude/commands/opsx/explore.md
 create mode 100644 .claude/commands/opsx/ff.md
 create mode 100644 .claude/commands/opsx/new.md
 create mode 100644 .claude/commands/opsx/onboard.md
 create mode 100644 .claude/commands/opsx/sync.md
 create mode 100644 .claude/commands/opsx/verify.md
 create mode 100644 .claude/skills/openspec-apply-change/SKILL.md
 create mode 100644 .claude/skills/openspec-archive-change/SKILL.md
 create mode 100644 .claude/skills/openspec-bulk-archive-change/SKILL.md
 create mode 100644 .claude/skills/openspec-continue-change/SKILL.md
 create mode 100644 .claude/skills/openspec-explore/SKILL.md
 create mode 100644 .claude/skills/openspec-ff-change/SKILL.md
 create mode 100644 .claude/skills/openspec-new-change/SKILL.md
 create mode 100644 .claude/skills/openspec-onboard/SKILL.md
 create mode 100644 .claude/skills/openspec-sync-specs/SKILL.md
 create mode 100644 .claude/skills/openspec-verify-change/SKILL.md
 create mode 100644 openspec/config.yaml

diff --git a/.claude/CLAUDE.md b/.claude/CLAUDE.md
new file mode 100644
index 0000000..be65129
--- /dev/null
+++ b/.claude/CLAUDE.md
@@ -0,0 +1,59 @@
+# Project instructions
+
+## Getting started
+
+Before starting any work on this project, always read the CONTRIBUTING.md file to understand the project's contribution guidelines and requirements.
+
+## Running tests
+
+This project uses environment variables stored in a `.env` file for database connection configuration. When running tests, these variables must be properly sourced into the environment.
+
+To run the test suite:
+
+```bash
+set -a && source .env && set +a && npm test
+```
+
+This command performs the following steps:
+
+1. `set -a` — Enables the allexport option, which automatically exports all variables that are set or modified.
+2. `source .env` — Sources the `.env` file, loading all environment variables.
+3. `set +a` — Disables the allexport option.
+4. `npm test` — Runs the test suite with the environment variables now available.
+
+### Important notes
+
+- Ensure a `.env` file exists in the project root before running tests.
+- The `.env` file should contain all necessary database connection parameters.
+- Never commit the `.env` file to version control as it may contain sensitive credentials.
+
+## Environment variables
+
+The project relies on environment variables for database configuration. Check the `.env.example` file (if present) or the project documentation for required variables.
+
+## IntelliJ IDE integration
+
+This project uses IntelliJ IDEA with MCP server integration for code analysis and problem detection.
+
+### Checking for problems
+
+When checking files for problems using the `mcp__intellij__get_file_problems` tool:
+
+- **Always set `errorsOnly: false`** to include both errors and warnings
+- Always specify the `projectPath` parameter to avoid ambiguity when multiple projects are open
+- Include both SonarQube and IDE warnings to ensure comprehensive code quality checks
+
+Example:
+```typescript
+mcp__intellij__get_file_problems({
+  filePath: "src/parser.ts",
+  projectPath: "/Users/gri306/Code/sof-mssql",
+  errorsOnly: false  // IMPORTANT: Include warnings
+})
+```
+
+Warnings often catch important issues such as:
+- Using deprecated APIs (e.g., `isNaN` vs `Number.isNaN`)
+- Type validation requiring specific error types (e.g., `TypeError` for type checks)
+- Complex regex patterns that should be simplified
+- Code quality issues flagged by SonarQube
diff --git a/.claude/commands/opsx/apply.md b/.claude/commands/opsx/apply.md
new file mode 100644
index 0000000..ae14f0f
--- /dev/null
+++ b/.claude/commands/opsx/apply.md
@@ -0,0 +1,152 @@
+---
+name: "OPSX: Apply"
+description: Implement tasks from an OpenSpec change (Experimental)
+category: Workflow
+tags: [workflow, artifacts, experimental]
+---
+
+Implement tasks from an OpenSpec change.
+
+**Input**: Optionally specify a change name (e.g., `/opsx:apply add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **Select the change**
+
+   If a name is provided, use it. Otherwise:
+   - Infer from conversation context if the user mentioned a change
+   - Auto-select if only one active change exists
+   - If ambiguous, run `openspec list --json` to get available changes and use the **AskUserQuestion tool** to let the user select
+
+   Always announce: "Using change: <name>" and how to override (e.g., `/opsx:apply <other>`).
+
+2. **Check status to understand the schema**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to understand:
+   - `schemaName`: The workflow being used (e.g., "spec-driven")
+   - Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
+
+3. **Get apply instructions**
+
+   ```bash
+   openspec instructions apply --change "<name>" --json
+   ```
+
+   This returns:
+   - `contextFiles`: artifact ID -> array of concrete file paths (varies by schema)
+   - Progress (total, complete, remaining)
+   - Task list with status
+   - Dynamic instruction based on current state
+
+   **Handle states:**
+   - If `state: "blocked"` (missing artifacts): show message, suggest using `/opsx:continue`
+   - If `state: "all_done"`: congratulate, suggest archive
+   - Otherwise: proceed to implementation
+
+4. **Read context files**
+
+   Read every file path listed under `contextFiles` from the apply instructions output.
+   The files depend on the schema being used:
+   - **spec-driven**: proposal, specs, design, tasks
+   - Other schemas: follow the contextFiles from CLI output
+
+5. **Show current progress**
+
+   Display:
+   - Schema being used
+   - Progress: "N/M tasks complete"
+   - Remaining tasks overview
+   - Dynamic instruction from CLI
+
+6. **Implement tasks (loop until done or blocked)**
+
+   For each pending task:
+   - Show which task is being worked on
+   - Make the code changes required
+   - Keep changes minimal and focused
+   - Mark task complete in the tasks file: `- [ ]` → `- [x]`
+   - Continue to next task
+
+   **Pause if:**
+   - Task is unclear → ask for clarification
+   - Implementation reveals a design issue → suggest updating artifacts
+   - Error or blocker encountered → report and wait for guidance
+   - User interrupts
+
+7. **On completion or pause, show status**
+
+   Display:
+   - Tasks completed this session
+   - Overall progress: "N/M tasks complete"
+   - If all done: suggest archive
+   - If paused: explain why and wait for guidance
+
+**Output During Implementation**
+
+```
+## Implementing: <change-name> (schema: <schema-name>)
+
+Working on task 3/7: <task description>
+[...implementation happening...]
+✓ Task complete
+
+Working on task 4/7: <task description>
+[...implementation happening...]
+✓ Task complete
+```
+
+**Output On Completion**
+
+```
+## Implementation Complete
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Progress:** 7/7 tasks complete ✓
+
+### Completed This Session
+- [x] Task 1
+- [x] Task 2
+...
+
+All tasks complete! You can archive this change with `/opsx:archive`.
+```
+
+**Output On Pause (Issue Encountered)**
+
+```
+## Implementation Paused
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Progress:** 4/7 tasks complete
+
+### Issue Encountered
+<description of the issue>
+
+**Options:**
+1. <option 1>
+2. <option 2>
+3. Other approach
+
+What would you like to do?
+```
+
+**Guardrails**
+- Keep going through tasks until done or blocked
+- Always read context files before starting (from the apply instructions output)
+- If task is ambiguous, pause and ask before implementing
+- If implementation reveals issues, pause and suggest artifact updates
+- Keep code changes minimal and scoped to each task
+- Update task checkbox immediately after completing each task
+- Pause on errors, blockers, or unclear requirements - don't guess
+- Use contextFiles from CLI output, don't assume specific file names
+
+**Fluid Workflow Integration**
+
+This skill supports the "actions on a change" model:
+
+- **Can be invoked anytime**: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
+- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly
diff --git a/.claude/commands/opsx/archive.md b/.claude/commands/opsx/archive.md
new file mode 100644
index 0000000..5e91608
--- /dev/null
+++ b/.claude/commands/opsx/archive.md
@@ -0,0 +1,157 @@
+---
+name: "OPSX: Archive"
+description: Archive a completed change in the experimental workflow
+category: Workflow
+tags: [workflow, archive, experimental]
+---
+
+Archive a completed change in the experimental workflow.
+
+**Input**: Optionally specify a change name after `/opsx:archive` (e.g., `/opsx:archive add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **If no change name provided, prompt for selection**
+
+   Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
+
+   Show only active changes (not already archived).
+   Include the schema used for each change if available.
+
+   **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
+
+2. **Check artifact completion status**
+
+   Run `openspec status --change "<name>" --json` to check artifact completion.
+
+   Parse the JSON to understand:
+   - `schemaName`: The workflow being used
+   - `artifacts`: List of artifacts with their status (`done` or other)
+
+   **If any artifacts are not `done`:**
+   - Display warning listing incomplete artifacts
+   - Prompt user for confirmation to continue
+   - Proceed if user confirms
+
+3. **Check task completion status**
+
+   Read the tasks file (typically `tasks.md`) to check for incomplete tasks.
+
+   Count tasks marked with `- [ ]` (incomplete) vs `- [x]` (complete).
+
+   **If incomplete tasks found:**
+   - Display warning showing count of incomplete tasks
+   - Prompt user for confirmation to continue
+   - Proceed if user confirms
+
+   **If no tasks file exists:** Proceed without task-related warning.
+
+4. **Assess delta spec sync state**
+
+   Check for delta specs at `openspec/changes/<name>/specs/`. If none exist, proceed without sync prompt.
+
+   **If delta specs exist:**
+   - Compare each delta spec with its corresponding main spec at `openspec/specs/<capability>/spec.md`
+   - Determine what changes would be applied (adds, modifications, removals, renames)
+   - Show a combined summary before prompting
+
+   **Prompt options:**
+   - If changes needed: "Sync now (recommended)", "Archive without syncing"
+   - If already synced: "Archive now", "Sync anyway", "Cancel"
+
+   If user chooses sync, use Task tool (subagent_type: "general-purpose", prompt: "Use Skill tool to invoke openspec-sync-specs for change '<name>'. Delta spec analysis: <include the analyzed delta spec summary>"). Proceed to archive regardless of choice.
+
+5. **Perform the archive**
+
+   Create the archive directory if it doesn't exist:
+   ```bash
+   mkdir -p openspec/changes/archive
+   ```
+
+   Generate target name using current date: `YYYY-MM-DD-<change-name>`
+
+   **Check if target already exists:**
+   - If yes: Fail with error, suggest renaming existing archive or using different date
+   - If no: Move the change directory to archive
+
+   ```bash
+   mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
+   ```
+
+6. **Display summary**
+
+   Show archive completion summary including:
+   - Change name
+   - Schema that was used
+   - Archive location
+   - Spec sync status (synced / sync skipped / no delta specs)
+   - Note about any warnings (incomplete artifacts/tasks)
+
+**Output On Success**
+
+```
+## Archive Complete
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
+**Specs:** ✓ Synced to main specs
+
+All artifacts complete. All tasks complete.
+```
+
+**Output On Success (No Delta Specs)**
+
+```
+## Archive Complete
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
+**Specs:** No delta specs
+
+All artifacts complete. All tasks complete.
+```
+
+**Output On Success With Warnings**
+
+```
+## Archive Complete (with warnings)
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
+**Specs:** Sync skipped (user chose to skip)
+
+**Warnings:**
+- Archived with 2 incomplete artifacts
+- Archived with 3 incomplete tasks
+- Delta spec sync was skipped (user chose to skip)
+
+Review the archive if this was not intentional.
+```
+
+**Output On Error (Archive Exists)**
+
+```
+## Archive Failed
+
+**Change:** <change-name>
+**Target:** openspec/changes/archive/YYYY-MM-DD-<name>/
+
+Target archive directory already exists.
+
+**Options:**
+1. Rename the existing archive
+2. Delete the existing archive if it's a duplicate
+3. Wait until a different date to archive
+```
+
+**Guardrails**
+- Always prompt for change selection if not provided
+- Use artifact graph (openspec status --json) for completion checking
+- Don't block archive on warnings - just inform and confirm
+- Preserve .openspec.yaml when moving to archive (it moves with the directory)
+- Show clear summary of what happened
+- If sync is requested, use the Skill tool to invoke `openspec-sync-specs` (agent-driven)
+- If delta specs exist, always run the sync assessment and show the combined summary before prompting
diff --git a/.claude/commands/opsx/bulk-archive.md b/.claude/commands/opsx/bulk-archive.md
new file mode 100644
index 0000000..1284d3d
--- /dev/null
+++ b/.claude/commands/opsx/bulk-archive.md
@@ -0,0 +1,242 @@
+---
+name: "OPSX: Bulk Archive"
+description: Archive multiple completed changes at once
+category: Workflow
+tags: [workflow, archive, experimental, bulk]
+---
+
+Archive multiple completed changes in a single operation.
+
+This skill allows you to batch-archive changes, handling spec conflicts intelligently by checking the codebase to determine what's actually implemented.
+
+**Input**: None required (prompts for selection)
+
+**Steps**
+
+1. **Get active changes**
+
+   Run `openspec list --json` to get all active changes.
+
+   If no active changes exist, inform user and stop.
+
+2. **Prompt for change selection**
+
+   Use **AskUserQuestion tool** with multi-select to let user choose changes:
+   - Show each change with its schema
+   - Include an option for "All changes"
+   - Allow any number of selections (1+ works, 2+ is the typical use case)
+
+   **IMPORTANT**: Do NOT auto-select. Always let the user choose.
+
+3. **Batch validation - gather status for all selected changes**
+
+   For each selected change, collect:
+
+   a. **Artifact status** - Run `openspec status --change "<name>" --json`
+      - Parse `schemaName` and `artifacts` list
+      - Note which artifacts are `done` vs other states
+
+   b. **Task completion** - Read `openspec/changes/<name>/tasks.md`
+      - Count `- [ ]` (incomplete) vs `- [x]` (complete)
+      - If no tasks file exists, note as "No tasks"
+
+   c. **Delta specs** - Check `openspec/changes/<name>/specs/` directory
+      - List which capability specs exist
+      - For each, extract requirement names (lines matching `### Requirement: <name>`)
+
+4. **Detect spec conflicts**
+
+   Build a map of `capability -> [changes that touch it]`:
+
+   ```
+   auth -> [change-a, change-b]  <- CONFLICT (2+ changes)
+   api  -> [change-c]            <- OK (only 1 change)
+   ```
+
+   A conflict exists when 2+ selected changes have delta specs for the same capability.
+
+5. **Resolve conflicts agentically**
+
+   **For each conflict**, investigate the codebase:
+
+   a. **Read the delta specs** from each conflicting change to understand what each claims to add/modify
+
+   b. **Search the codebase** for implementation evidence:
+      - Look for code implementing requirements from each delta spec
+      - Check for related files, functions, or tests
+
+   c. **Determine resolution**:
+      - If only one change is actually implemented -> sync that one's specs
+      - If both implemented -> apply in chronological order (older first, newer overwrites)
+      - If neither implemented -> skip spec sync, warn user
+
+   d. **Record resolution** for each conflict:
+      - Which change's specs to apply
+      - In what order (if both)
+      - Rationale (what was found in codebase)
+
+6. **Show consolidated status table**
+
+   Display a table summarizing all changes:
+
+   ```
+   | Change              | Artifacts | Tasks | Specs   | Conflicts | Status |
+   |---------------------|-----------|-------|---------|-----------|--------|
+   | schema-management   | Done      | 5/5   | 2 delta | None      | Ready  |
+   | project-config      | Done      | 3/3   | 1 delta | None      | Ready  |
+   | add-oauth           | Done      | 4/4   | 1 delta | auth (!)  | Ready* |
+   | add-verify-skill    | 1 left    | 2/5   | None    | None      | Warn   |
+   ```
+
+   For conflicts, show the resolution:
+   ```
+   * Conflict resolution:
+     - auth spec: Will apply add-oauth then add-jwt (both implemented, chronological order)
+   ```
+
+   For incomplete changes, show warnings:
+   ```
+   Warnings:
+   - add-verify-skill: 1 incomplete artifact, 3 incomplete tasks
+   ```
+
+7. **Confirm batch operation**
+
+   Use **AskUserQuestion tool** with a single confirmation:
+
+   - "Archive N changes?" with options based on status
+   - Options might include:
+     - "Archive all N changes"
+     - "Archive only N ready changes (skip incomplete)"
+     - "Cancel"
+
+   If there are incomplete changes, make clear they'll be archived with warnings.
+
+8. **Execute archive for each confirmed change**
+
+   Process changes in the determined order (respecting conflict resolution):
+
+   a. **Sync specs** if delta specs exist:
+      - Use the openspec-sync-specs approach (agent-driven intelligent merge)
+      - For conflicts, apply in resolved order
+      - Track if sync was done
+
+   b. **Perform the archive**:
+      ```bash
+      mkdir -p openspec/changes/archive
+      mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
+      ```
+
+   c. **Track outcome** for each change:
+      - Success: archived successfully
+      - Failed: error during archive (record error)
+      - Skipped: user chose not to archive (if applicable)
+
+9. **Display summary**
+
+   Show final results:
+
+   ```
+   ## Bulk Archive Complete
+
+   Archived 3 changes:
+   - schema-management-cli -> archive/2026-01-19-schema-management-cli/
+   - project-config -> archive/2026-01-19-project-config/
+   - add-oauth -> archive/2026-01-19-add-oauth/
+
+   Skipped 1 change:
+   - add-verify-skill (user chose not to archive incomplete)
+
+   Spec sync summary:
+   - 4 delta specs synced to main specs
+   - 1 conflict resolved (auth: applied both in chronological order)
+   ```
+
+   If any failures:
+   ```
+   Failed 1 change:
+   - some-change: Archive directory already exists
+   ```
+
+**Conflict Resolution Examples**
+
+Example 1: Only one implemented
+```
+Conflict: specs/auth/spec.md touched by [add-oauth, add-jwt]
+
+Checking add-oauth:
+- Delta adds "OAuth Provider Integration" requirement
+- Searching codebase... found src/auth/oauth.ts implementing OAuth flow
+
+Checking add-jwt:
+- Delta adds "JWT Token Handling" requirement
+- Searching codebase... no JWT implementation found
+
+Resolution: Only add-oauth is implemented. Will sync add-oauth specs only.
+```
+
+Example 2: Both implemented
+```
+Conflict: specs/api/spec.md touched by [add-rest-api, add-graphql]
+
+Checking add-rest-api (created 2026-01-10):
+- Delta adds "REST Endpoints" requirement
+- Searching codebase... found src/api/rest.ts
+
+Checking add-graphql (created 2026-01-15):
+- Delta adds "GraphQL Schema" requirement
+- Searching codebase... found src/api/graphql.ts
+
+Resolution: Both implemented. Will apply add-rest-api specs first,
+then add-graphql specs (chronological order, newer takes precedence).
+```
+
+**Output On Success**
+
+```
+## Bulk Archive Complete
+
+Archived N changes:
+- <change-1> -> archive/YYYY-MM-DD-<change-1>/
+- <change-2> -> archive/YYYY-MM-DD-<change-2>/
+
+Spec sync summary:
+- N delta specs synced to main specs
+- No conflicts (or: M conflicts resolved)
+```
+
+**Output On Partial Success**
+
+```
+## Bulk Archive Complete (partial)
+
+Archived N changes:
+- <change-1> -> archive/YYYY-MM-DD-<change-1>/
+
+Skipped M changes:
+- <change-2> (user chose not to archive incomplete)
+
+Failed K changes:
+- <change-3>: Archive directory already exists
+```
+
+**Output When No Changes**
+
+```
+## No Changes to Archive
+
+No active changes found. Create a new change to get started.
+```
+
+**Guardrails**
+- Allow any number of changes (1+ is fine, 2+ is the typical use case)
+- Always prompt for selection, never auto-select
+- Detect spec conflicts early and resolve by checking codebase
+- When both changes are implemented, apply specs in chronological order
+- Skip spec sync only when implementation is missing (warn user)
+- Show clear per-change status before confirming
+- Use single confirmation for entire batch
+- Track and report all outcomes (success/skip/fail)
+- Preserve .openspec.yaml when moving to archive
+- Archive directory target uses current date: YYYY-MM-DD-<name>
+- If archive target exists, fail that change but continue with others
diff --git a/.claude/commands/opsx/continue.md b/.claude/commands/opsx/continue.md
new file mode 100644
index 0000000..af255c6
--- /dev/null
+++ b/.claude/commands/opsx/continue.md
@@ -0,0 +1,114 @@
+---
+name: "OPSX: Continue"
+description: Continue working on a change - create the next artifact (Experimental)
+category: Workflow
+tags: [workflow, artifacts, experimental]
+---
+
+Continue working on a change by creating the next artifact.
+
+**Input**: Optionally specify a change name after `/opsx:continue` (e.g., `/opsx:continue add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **If no change name provided, prompt for selection**
+
+   Run `openspec list --json` to get available changes sorted by most recently modified. Then use the **AskUserQuestion tool** to let the user select which change to work on.
+
+   Present the top 3-4 most recently modified changes as options, showing:
+   - Change name
+   - Schema (from `schema` field if present, otherwise "spec-driven")
+   - Status (e.g., "0/5 tasks", "complete", "no tasks")
+   - How recently it was modified (from `lastModified` field)
+
+   Mark the most recently modified change as "(Recommended)" since it's likely what the user wants to continue.
+
+   **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
+
+2. **Check current status**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to understand current state. The response includes:
+   - `schemaName`: The workflow schema being used (e.g., "spec-driven")
+   - `artifacts`: Array of artifacts with their status ("done", "ready", "blocked")
+   - `isComplete`: Boolean indicating if all artifacts are complete
+
+3. **Act based on status**:
+
+   ---
+
+   **If all artifacts are complete (`isComplete: true`)**:
+   - Congratulate the user
+   - Show final status including the schema used
+   - Suggest: "All artifacts created! You can now implement this change with `/opsx:apply` or archive it with `/opsx:archive`."
+   - STOP
+
+   ---
+
+   **If artifacts are ready to create** (status shows artifacts with `status: "ready"`):
+   - Pick the FIRST artifact with `status: "ready"` from the status output
+   - Get its instructions:
+     ```bash
+     openspec instructions <artifact-id> --change "<name>" --json
+     ```
+   - Parse the JSON. The key fields are:
+     - `context`: Project background (constraints for you - do NOT include in output)
+     - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
+     - `template`: The structure to use for your output file
+     - `instruction`: Schema-specific guidance
+     - `outputPath`: Where to write the artifact
+     - `dependencies`: Completed artifacts to read for context
+   - **Create the artifact file**:
+     - Read any completed dependency files for context
+     - Use `template` as the structure - fill in its sections
+     - Apply `context` and `rules` as constraints when writing - but do NOT copy them into the file
+     - Write to the output path specified in instructions
+   - Show what was created and what's now unlocked
+   - STOP after creating ONE artifact
+
+   ---
+
+   **If no artifacts are ready (all blocked)**:
+   - This shouldn't happen with a valid schema
+   - Show status and suggest checking for issues
+
+4. **After creating an artifact, show progress**
+   ```bash
+   openspec status --change "<name>"
+   ```
+
+**Output**
+
+After each invocation, show:
+- Which artifact was created
+- Schema workflow being used
+- Current progress (N/M complete)
+- What artifacts are now unlocked
+- Prompt: "Run `/opsx:continue` to create the next artifact"
+
+**Artifact Creation Guidelines**
+
+The artifact types and their purpose depend on the schema. Use the `instruction` field from the instructions output to understand what to create.
+
+Common artifact patterns:
+
+**spec-driven schema** (proposal → specs → design → tasks):
+- **proposal.md**: Ask user about the change if not clear. Fill in Why, What Changes, Capabilities, Impact.
+  - The Capabilities section is critical - each capability listed will need a spec file.
+- **specs/<capability>/spec.md**: Create one spec per capability listed in the proposal's Capabilities section (use the capability name, not the change name).
+- **design.md**: Document technical decisions, architecture, and implementation approach.
+- **tasks.md**: Break down implementation into checkboxed tasks.
+
+For other schemas, follow the `instruction` field from the CLI output.
+
+**Guardrails**
+- Create ONE artifact per invocation
+- Always read dependency artifacts before creating a new one
+- Never skip artifacts or create out of order
+- If context is unclear, ask the user before creating
+- Verify the artifact file exists after writing before marking progress
+- Use the schema's artifact sequence, don't assume specific artifact names
+- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
+  - Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
+  - These guide what you write, but should never appear in the output
diff --git a/.claude/commands/opsx/explore.md b/.claude/commands/opsx/explore.md
new file mode 100644
index 0000000..1757907
--- /dev/null
+++ b/.claude/commands/opsx/explore.md
@@ -0,0 +1,173 @@
+---
+name: "OPSX: Explore"
+description: "Enter explore mode - think through ideas, investigate problems, clarify requirements"
+category: Workflow
+tags: [workflow, explore, experimental, thinking]
+---
+
+Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.
+
+**IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first and create a change proposal. You MAY create OpenSpec artifacts (proposals, designs, specs) if the user asks—that's capturing thinking, not implementing.
+
+**This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.
+
+**Input**: The argument after `/opsx:explore` is whatever the user wants to think about. Could be:
+- A vague idea: "real-time collaboration"
+- A specific problem: "the auth system is getting unwieldy"
+- A change name: "add-dark-mode" (to explore in context of that change)
+- A comparison: "postgres vs sqlite for this"
+- Nothing (just enter explore mode)
+
+---
+
+## The Stance
+
+- **Curious, not prescriptive** - Ask questions that emerge naturally, don't follow a script
+- **Open threads, not interrogations** - Surface multiple interesting directions and let the user follow what resonates. Don't funnel them through a single path of questions.
+- **Visual** - Use ASCII diagrams liberally when they'd help clarify thinking
+- **Adaptive** - Follow interesting threads, pivot when new information emerges
+- **Patient** - Don't rush to conclusions, let the shape of the problem emerge
+- **Grounded** - Explore the actual codebase when relevant, don't just theorize
+
+---
+
+## What You Might Do
+
+Depending on what the user brings, you might:
+
+**Explore the problem space**
+- Ask clarifying questions that emerge from what they said
+- Challenge assumptions
+- Reframe the problem
+- Find analogies
+
+**Investigate the codebase**
+- Map existing architecture relevant to the discussion
+- Find integration points
+- Identify patterns already in use
+- Surface hidden complexity
+
+**Compare options**
+- Brainstorm multiple approaches
+- Build comparison tables
+- Sketch tradeoffs
+- Recommend a path (if asked)
+
+**Visualize**
+```
+┌─────────────────────────────────────────┐
+│     Use ASCII diagrams liberally        │
+├─────────────────────────────────────────┤
+│                                         │
+│      ┌────────┐         ┌────────┐      │
+│      │ State  │────────▶│ State  │      │
+│      │   A    │         │   B    │      │
+│      └────────┘         └────────┘      │
+│                                         │
+│   System diagrams, state machines,      │
+│   data flows, architecture sketches,    │
+│   dependency graphs, comparison tables  │
+│                                         │
+└─────────────────────────────────────────┘
+```
+
+**Surface risks and unknowns**
+- Identify what could go wrong
+- Find gaps in understanding
+- Suggest spikes or investigations
+
+---
+
+## OpenSpec Awareness
+
+You have full context of the OpenSpec system. Use it naturally, don't force it.
+
+### Check for context
+
+At the start, quickly check what exists:
+```bash
+openspec list --json
+```
+
+This tells you:
+- If there are active changes
+- Their names, schemas, and status
+- What the user might be working on
+
+If the user mentioned a specific change name, read its artifacts for context.
+
+### When no change exists
+
+Think freely. When insights crystallize, you might offer:
+
+- "This feels solid enough to start a change. Want me to create a proposal?"
+- Or keep exploring - no pressure to formalize
+
+### When a change exists
+
+If the user mentions a change or you detect one is relevant:
+
+1. **Read existing artifacts for context**
+   - `openspec/changes/<name>/proposal.md`
+   - `openspec/changes/<name>/design.md`
+   - `openspec/changes/<name>/tasks.md`
+   - etc.
+
+2. **Reference them naturally in conversation**
+   - "Your design mentions using Redis, but we just realized SQLite fits better..."
+   - "The proposal scopes this to premium users, but we're now thinking everyone..."
+
+3. **Offer to capture when decisions are made**
+
+    | Insight Type               | Where to Capture               |
+    |----------------------------|--------------------------------|
+    | New requirement discovered | `specs/<capability>/spec.md` |
+    | Requirement changed        | `specs/<capability>/spec.md` |
+    | Design decision made       | `design.md`                  |
+    | Scope changed              | `proposal.md`                |
+    | New work identified        | `tasks.md`                   |
+    | Assumption invalidated     | Relevant artifact              |
+
+   Example offers:
+   - "That's a design decision. Capture it in design.md?"
+   - "This is a new requirement. Add it to specs?"
+   - "This changes scope. Update the proposal?"
+
+4. **The user decides** - Offer and move on. Don't pressure. Don't auto-capture.
+
+---
+
+## What You Don't Have To Do
+
+- Follow a script
+- Ask the same questions every time
+- Produce a specific artifact
+- Reach a conclusion
+- Stay on topic if a tangent is valuable
+- Be brief (this is thinking time)
+
+---
+
+## Ending Discovery
+
+There's no required ending. Discovery might:
+
+- **Flow into a proposal**: "Ready to start? I can create a change proposal."
+- **Result in artifact updates**: "Updated design.md with these decisions"
+- **Just provide clarity**: User has what they need, moves on
+- **Continue later**: "We can pick this up anytime"
+
+When things crystallize, you might offer a summary - but it's optional. Sometimes the thinking IS the value.
+
+---
+
+## Guardrails
+
+- **Don't implement** - Never write code or implement features. Creating OpenSpec artifacts is fine, writing application code is not.
+- **Don't fake understanding** - If something is unclear, dig deeper
+- **Don't rush** - Discovery is thinking time, not task time
+- **Don't force structure** - Let patterns emerge naturally
+- **Don't auto-capture** - Offer to save insights, don't just do it
+- **Do visualize** - A good diagram is worth many paragraphs
+- **Do explore the codebase** - Ground discussions in reality
+- **Do question assumptions** - Including the user's and your own
diff --git a/.claude/commands/opsx/ff.md b/.claude/commands/opsx/ff.md
new file mode 100644
index 0000000..69f749c
--- /dev/null
+++ b/.claude/commands/opsx/ff.md
@@ -0,0 +1,97 @@
+---
+name: "OPSX: Fast Forward"
+description: Create a change and generate all artifacts needed for implementation in one go
+category: Workflow
+tags: [workflow, artifacts, experimental]
+---
+
+Fast-forward through artifact creation - generate everything needed to start implementation.
+
+**Input**: The argument after `/opsx:ff` is the change name (kebab-case), OR a description of what the user wants to build.
+
+**Steps**
+
+1. **If no input provided, ask what they want to build**
+
+   Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
+   > "What change do you want to work on? Describe what you want to build or fix."
+
+   From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
+
+   **IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
+
+2. **Create the change directory**
+   ```bash
+   openspec new change "<name>"
+   ```
+   This creates a scaffolded change at `openspec/changes/<name>/`.
+
+3. **Get the artifact build order**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to get:
+   - `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
+   - `artifacts`: list of all artifacts with their status and dependencies
+
+4. **Create artifacts in sequence until apply-ready**
+
+   Use the **TodoWrite tool** to track progress through the artifacts.
+
+   Loop through artifacts in dependency order (artifacts with no pending dependencies first):
+
+   a. **For each artifact that is `ready` (dependencies satisfied)**:
+      - Get instructions:
+        ```bash
+        openspec instructions <artifact-id> --change "<name>" --json
+        ```
+      - The instructions JSON includes:
+        - `context`: Project background (constraints for you - do NOT include in output)
+        - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
+        - `template`: The structure to use for your output file
+        - `instruction`: Schema-specific guidance for this artifact type
+        - `outputPath`: Where to write the artifact
+        - `dependencies`: Completed artifacts to read for context
+      - Read any completed dependency files for context
+      - Create the artifact file using `template` as the structure
+      - Apply `context` and `rules` as constraints - but do NOT copy them into the file
+      - Show brief progress: "✓ Created <artifact-id>"
+
+   b. **Continue until all `applyRequires` artifacts are complete**
+      - After creating each artifact, re-run `openspec status --change "<name>" --json`
+      - Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
+      - Stop when all `applyRequires` artifacts are done
+
+   c. **If an artifact requires user input** (unclear context):
+      - Use **AskUserQuestion tool** to clarify
+      - Then continue with creation
+
+5. **Show final status**
+   ```bash
+   openspec status --change "<name>"
+   ```
+
+**Output**
+
+After completing all artifacts, summarize:
+- Change name and location
+- List of artifacts created with brief descriptions
+- What's ready: "All artifacts created! Ready for implementation."
+- Prompt: "Run `/opsx:apply` to start implementing."
+
+**Artifact Creation Guidelines**
+
+- Follow the `instruction` field from `openspec instructions` for each artifact type
+- The schema defines what each artifact should contain - follow it
+- Read dependency artifacts for context before creating new ones
+- Use `template` as the structure for your output file - fill in its sections
+- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
+  - Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
+  - These guide what you write, but should never appear in the output
+
+**Guardrails**
+- Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
+- Always read dependency artifacts before creating a new one
+- If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum
+- If a change with that name already exists, ask if user wants to continue it or create a new one
+- Verify each artifact file exists after writing before proceeding to next
diff --git a/.claude/commands/opsx/new.md b/.claude/commands/opsx/new.md
new file mode 100644
index 0000000..ef26cfa
--- /dev/null
+++ b/.claude/commands/opsx/new.md
@@ -0,0 +1,69 @@
+---
+name: "OPSX: New"
+description: Start a new change using the experimental artifact workflow (OPSX)
+category: Workflow
+tags: [workflow, artifacts, experimental]
+---
+
+Start a new change using the experimental artifact-driven approach.
+
+**Input**: The argument after `/opsx:new` is the change name (kebab-case), OR a description of what the user wants to build.
+
+**Steps**
+
+1. **If no input provided, ask what they want to build**
+
+   Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
+   > "What change do you want to work on? Describe what you want to build or fix."
+
+   From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
+
+   **IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
+
+2. **Determine the workflow schema**
+
+   Use the default schema (omit `--schema`) unless the user explicitly requests a different workflow.
+
+   **Use a different schema only if the user mentions:**
+   - A specific schema name → use `--schema <name>`
+   - "show workflows" or "what workflows" → run `openspec schemas --json` and let them choose
+
+   **Otherwise**: Omit `--schema` to use the default.
+
+3. **Create the change directory**
+   ```bash
+   openspec new change "<name>"
+   ```
+   Add `--schema <name>` only if the user requested a specific workflow.
+   This creates a scaffolded change at `openspec/changes/<name>/` with the selected schema.
+
+4. **Show the artifact status**
+   ```bash
+   openspec status --change "<name>"
+   ```
+   This shows which artifacts need to be created and which are ready (dependencies satisfied).
+
+5. **Get instructions for the first artifact**
+   The first artifact depends on the schema. Check the status output to find the first artifact with status "ready".
+   ```bash
+   openspec instructions <first-artifact-id> --change "<name>"
+   ```
+   This outputs the template and context for creating the first artifact.
+
+6. **STOP and wait for user direction**
+
+**Output**
+
+After completing the steps, summarize:
+- Change name and location
+- Schema/workflow being used and its artifact sequence
+- Current status (0/N artifacts complete)
+- The template for the first artifact
+- Prompt: "Ready to create the first artifact? Run `/opsx:continue` or just describe what this change is about and I'll draft it."
+
+**Guardrails**
+- Do NOT create any artifacts yet - just show the instructions
+- Do NOT advance beyond showing the first artifact template
+- If the name is invalid (not kebab-case), ask for a valid name
+- If a change with that name already exists, suggest using `/opsx:continue` instead
+- Pass --schema if using a non-default workflow
diff --git a/.claude/commands/opsx/onboard.md b/.claude/commands/opsx/onboard.md
new file mode 100644
index 0000000..10a7eb6
--- /dev/null
+++ b/.claude/commands/opsx/onboard.md
@@ -0,0 +1,550 @@
+---
+name: "OPSX: Onboard"
+description: Guided onboarding - walk through a complete OpenSpec workflow cycle with narration
+category: Workflow
+tags: [workflow, onboarding, tutorial, learning]
+---
+
+Guide the user through their first complete OpenSpec workflow cycle. This is a teaching experience—you'll do real work in their codebase while explaining each step.
+
+---
+
+## Preflight
+
+Before starting, check if the OpenSpec CLI is installed:
+
+```bash
+# Unix/macOS
+openspec --version 2>&1 || echo "CLI_NOT_INSTALLED"
+# Windows (PowerShell)
+# if (Get-Command openspec -ErrorAction SilentlyContinue) { openspec --version } else { echo "CLI_NOT_INSTALLED" }
+```
+
+**If CLI not installed:**
+> OpenSpec CLI is not installed. Install it first, then come back to `/opsx:onboard`.
+
+Stop here if not installed.
+
+---
+
+## Phase 1: Welcome
+
+Display:
+
+```
+## Welcome to OpenSpec!
+
+I'll walk you through a complete change cycle—from idea to implementation—using a real task in your codebase. Along the way, you'll learn the workflow by doing it.
+
+**What we'll do:**
+1. Pick a small, real task in your codebase
+2. Explore the problem briefly
+3. Create a change (the container for our work)
+4. Build the artifacts: proposal → specs → design → tasks
+5. Implement the tasks
+6. Archive the completed change
+
+**Time:** ~15-20 minutes
+
+Let's start by finding something to work on.
+```
+
+---
+
+## Phase 2: Task Selection
+
+### Codebase Analysis
+
+Scan the codebase for small improvement opportunities. Look for:
+
+1. **TODO/FIXME comments** - Search for `TODO`, `FIXME`, `HACK`, `XXX` in code files
+2. **Missing error handling** - `catch` blocks that swallow errors, risky operations without try-catch
+3. **Functions without tests** - Cross-reference `src/` with test directories
+4. **Type issues** - `any` types in TypeScript files (`: any`, `as any`)
+5. **Debug artifacts** - `console.log`, `console.debug`, `debugger` statements in non-debug code
+6. **Missing validation** - User input handlers without validation
+
+Also check recent git activity:
+```bash
+# Unix/macOS
+git log --oneline -10 2>/dev/null || echo "No git history"
+# Windows (PowerShell)
+# git log --oneline -10 2>$null; if ($LASTEXITCODE -ne 0) { echo "No git history" }
+```
+
+### Present Suggestions
+
+From your analysis, present 3-4 specific suggestions:
+
+```
+## Task Suggestions
+
+Based on scanning your codebase, here are some good starter tasks:
+
+**1. [Most promising task]**
+   Location: `src/path/to/file.ts:42`
+   Scope: ~1-2 files, ~20-30 lines
+   Why it's good: [brief reason]
+
+**2. [Second task]**
+   Location: `src/another/file.ts`
+   Scope: ~1 file, ~15 lines
+   Why it's good: [brief reason]
+
+**3. [Third task]**
+   Location: [location]
+   Scope: [estimate]
+   Why it's good: [brief reason]
+
+**4. Something else?**
+   Tell me what you'd like to work on.
+
+Which task interests you? (Pick a number or describe your own)
+```
+
+**If nothing found:** Fall back to asking what the user wants to build:
+> I didn't find obvious quick wins in your codebase. What's something small you've been meaning to add or fix?
+
+### Scope Guardrail
+
+If the user picks or describes something too large (major feature, multi-day work):
+
+```
+That's a valuable task, but it's probably larger than ideal for your first OpenSpec run-through.
+
+For learning the workflow, smaller is better—it lets you see the full cycle without getting stuck in implementation details.
+
+**Options:**
+1. **Slice it smaller** - What's the smallest useful piece of [their task]? Maybe just [specific slice]?
+2. **Pick something else** - One of the other suggestions, or a different small task?
+3. **Do it anyway** - If you really want to tackle this, we can. Just know it'll take longer.
+
+What would you prefer?
+```
+
+Let the user override if they insist—this is a soft guardrail.
+
+---
+
+## Phase 3: Explore Demo
+
+Once a task is selected, briefly demonstrate explore mode:
+
+```
+Before we create a change, let me quickly show you **explore mode**—it's how you think through problems before committing to a direction.
+```
+
+Spend 1-2 minutes investigating the relevant code:
+- Read the file(s) involved
+- Draw a quick ASCII diagram if it helps
+- Note any considerations
+
+```
+## Quick Exploration
+
+[Your brief analysis—what you found, any considerations]
+
+┌─────────────────────────────────────────┐
+│   [Optional: ASCII diagram if helpful]  │
+└─────────────────────────────────────────┘
+
+Explore mode (`/opsx:explore`) is for this kind of thinking—investigating before implementing. You can use it anytime you need to think through a problem.
+
+Now let's create a change to hold our work.
+```
+
+**PAUSE** - Wait for user acknowledgment before proceeding.
+
+---
+
+## Phase 4: Create the Change
+
+**EXPLAIN:**
+```
+## Creating a Change
+
+A "change" in OpenSpec is a container for all the thinking and planning around a piece of work. It lives in `openspec/changes/<name>/` and holds your artifacts—proposal, specs, design, tasks.
+
+Let me create one for our task.
+```
+
+**DO:** Create the change with a derived kebab-case name:
+```bash
+openspec new change "<derived-name>"
+```
+
+**SHOW:**
+```
+Created: `openspec/changes/<name>/`
+
+The folder structure:
+```
+openspec/changes/<name>/
+├── proposal.md    ← Why we're doing this (empty, we'll fill it)
+├── design.md      ← How we'll build it (empty)
+├── specs/         ← Detailed requirements (empty)
+└── tasks.md       ← Implementation checklist (empty)
+```
+
+Now let's fill in the first artifact—the proposal.
+```
+
+---
+
+## Phase 5: Proposal
+
+**EXPLAIN:**
+```
+## The Proposal
+
+The proposal captures **why** we're making this change and **what** it involves at a high level. It's the "elevator pitch" for the work.
+
+I'll draft one based on our task.
+```
+
+**DO:** Draft the proposal content (don't save yet):
+
+```
+Here's a draft proposal:
+
+---
+
+## Why
+
+[1-2 sentences explaining the problem/opportunity]
+
+## What Changes
+
+[Bullet points of what will be different]
+
+## Capabilities
+
+### New Capabilities
+- `<capability-name>`: [brief description]
+
+### Modified Capabilities
+<!-- If modifying existing behavior -->
+
+## Impact
+
+- `src/path/to/file.ts`: [what changes]
+- [other files if applicable]
+
+---
+
+Does this capture the intent? I can adjust before we save it.
+```
+
+**PAUSE** - Wait for user approval/feedback.
+
+After approval, save the proposal:
+```bash
+openspec instructions proposal --change "<name>" --json
+```
+Then write the content to `openspec/changes/<name>/proposal.md`.
+
+```
+Proposal saved. This is your "why" document—you can always come back and refine it as understanding evolves.
+
+Next up: specs.
+```
+
+---
+
+## Phase 6: Specs
+
+**EXPLAIN:**
+```
+## Specs
+
+Specs define **what** we're building in precise, testable terms. They use a requirement/scenario format that makes expected behavior crystal clear.
+
+For a small task like this, we might only need one spec file.
+```
+
+**DO:** Create the spec file:
+```bash
+# Unix/macOS
+mkdir -p openspec/changes/<name>/specs/<capability-name>
+# Windows (PowerShell)
+# New-Item -ItemType Directory -Force -Path "openspec/changes/<name>/specs/<capability-name>"
+```
+
+Draft the spec content:
+
+```
+Here's the spec:
+
+---
+
+## ADDED Requirements
+
+### Requirement: <Name>
+
+<Description of what the system should do>
+
+#### Scenario: <Scenario name>
+
+- **WHEN** <trigger condition>
+- **THEN** <expected outcome>
+- **AND** <additional outcome if needed>
+
+---
+
+This format—WHEN/THEN/AND—makes requirements testable. You can literally read them as test cases.
+```
+
+Save to `openspec/changes/<name>/specs/<capability>/spec.md`.
+
+---
+
+## Phase 7: Design
+
+**EXPLAIN:**
+```
+## Design
+
+The design captures **how** we'll build it—technical decisions, tradeoffs, approach.
+
+For small changes, this might be brief. That's fine—not every change needs deep design discussion.
+```
+
+**DO:** Draft design.md:
+
+```
+Here's the design:
+
+---
+
+## Context
+
+[Brief context about the current state]
+
+## Goals / Non-Goals
+
+**Goals:**
+- [What we're trying to achieve]
+
+**Non-Goals:**
+- [What's explicitly out of scope]
+
+## Decisions
+
+### Decision 1: [Key decision]
+
+[Explanation of approach and rationale]
+
+---
+
+For a small task, this captures the key decisions without over-engineering.
+```
+
+Save to `openspec/changes/<name>/design.md`.
+
+---
+
+## Phase 8: Tasks
+
+**EXPLAIN:**
+```
+## Tasks
+
+Finally, we break the work into implementation tasks—checkboxes that drive the apply phase.
+
+These should be small, clear, and in logical order.
+```
+
+**DO:** Generate tasks based on specs and design:
+
+```
+Here are the implementation tasks:
+
+---
+
+## 1. [Category or file]
+
+- [ ] 1.1 [Specific task]
+- [ ] 1.2 [Specific task]
+
+## 2. Verify
+
+- [ ] 2.1 [Verification step]
+
+---
+
+Each checkbox becomes a unit of work in the apply phase. Ready to implement?
+```
+
+**PAUSE** - Wait for user to confirm they're ready to implement.
+
+Save to `openspec/changes/<name>/tasks.md`.
+
+---
+
+## Phase 9: Apply (Implementation)
+
+**EXPLAIN:**
+```
+## Implementation
+
+Now we implement each task, checking them off as we go. I'll announce each one and occasionally note how the specs/design informed the approach.
+```
+
+**DO:** For each task:
+
+1. Announce: "Working on task N: [description]"
+2. Implement the change in the codebase
+3. Reference specs/design naturally: "The spec says X, so I'm doing Y"
+4. Mark complete in tasks.md: `- [ ]` → `- [x]`
+5. Brief status: "✓ Task N complete"
+
+Keep narration light—don't over-explain every line of code.
+
+After all tasks:
+
+```
+## Implementation Complete
+
+All tasks done:
+- [x] Task 1
+- [x] Task 2
+- [x] ...
+
+The change is implemented! One more step—let's archive it.
+```
+
+---
+
+## Phase 10: Archive
+
+**EXPLAIN:**
+```
+## Archiving
+
+When a change is complete, we archive it. This moves it from `openspec/changes/` to `openspec/changes/archive/YYYY-MM-DD-<name>/`.
+
+Archived changes become your project's decision history—you can always find them later to understand why something was built a certain way.
+```
+
+**DO:**
+```bash
+openspec archive "<name>"
+```
+
+**SHOW:**
+```
+Archived to: `openspec/changes/archive/YYYY-MM-DD-<name>/`
+
+The change is now part of your project's history. The code is in your codebase, the decision record is preserved.
+```
+
+---
+
+## Phase 11: Recap & Next Steps
+
+```
+## Congratulations!
+
+You just completed a full OpenSpec cycle:
+
+1. **Explore** - Thought through the problem
+2. **New** - Created a change container
+3. **Proposal** - Captured WHY
+4. **Specs** - Defined WHAT in detail
+5. **Design** - Decided HOW
+6. **Tasks** - Broke it into steps
+7. **Apply** - Implemented the work
+8. **Archive** - Preserved the record
+
+This same rhythm works for any size change—a small fix or a major feature.
+
+---
+
+## Command Reference
+
+**Core workflow:**
+
+ | Command           | What it does                               |
+ |-------------------|--------------------------------------------|
+ | `/opsx:propose` | Create a change and generate all artifacts |
+ | `/opsx:explore` | Think through problems before/during work  |
+ | `/opsx:apply`   | Implement tasks from a change              |
+ | `/opsx:archive` | Archive a completed change                 |
+
+**Additional commands:**
+
+ | Command            | What it does                                             |
+ |--------------------|----------------------------------------------------------|
+ | `/opsx:new`      | Start a new change, step through artifacts one at a time |
+ | `/opsx:continue` | Continue working on an existing change                   |
+ | `/opsx:ff`       | Fast-forward: create all artifacts at once               |
+ | `/opsx:verify`   | Verify implementation matches artifacts                  |
+
+---
+
+## What's Next?
+
+Try `/opsx:propose` on something you actually want to build. You've got the rhythm now!
+```
+
+---
+
+## Graceful Exit Handling
+
+### User wants to stop mid-way
+
+If the user says they need to stop, want to pause, or seem disengaged:
+
+```
+No problem! Your change is saved at `openspec/changes/<name>/`.
+
+To pick up where we left off later:
+- `/opsx:continue <name>` - Resume artifact creation
+- `/opsx:apply <name>` - Jump to implementation (if tasks exist)
+
+The work won't be lost. Come back whenever you're ready.
+```
+
+Exit gracefully without pressure.
+
+### User just wants command reference
+
+If the user says they just want to see the commands or skip the tutorial:
+
+```
+## OpenSpec Quick Reference
+
+**Core workflow:**
+
+ | Command                  | What it does                               |
+ |--------------------------|--------------------------------------------|
+ | `/opsx:propose <name>` | Create a change and generate all artifacts |
+ | `/opsx:explore`        | Think through problems (no code changes)   |
+ | `/opsx:apply <name>`   | Implement tasks                            |
+ | `/opsx:archive <name>` | Archive when done                          |
+
+**Additional commands:**
+
+ | Command                   | What it does                        |
+ |---------------------------|-------------------------------------|
+ | `/opsx:new <name>`      | Start a new change, step by step    |
+ | `/opsx:continue <name>` | Continue an existing change         |
+ | `/opsx:ff <name>`       | Fast-forward: all artifacts at once |
+ | `/opsx:verify <name>`   | Verify implementation               |
+
+Try `/opsx:propose` to start your first change.
+```
+
+Exit gracefully.
+
+---
+
+## Guardrails
+
+- **Follow the EXPLAIN → DO → SHOW → PAUSE pattern** at key transitions (after explore, after proposal draft, after tasks, after archive)
+- **Keep narration light** during implementation—teach without lecturing
+- **Don't skip phases** even if the change is small—the goal is teaching the workflow
+- **Pause for acknowledgment** at marked points, but don't over-pause
+- **Handle exits gracefully**—never pressure the user to continue
+- **Use real codebase tasks**—don't simulate or use fake examples
+- **Adjust scope gently**—guide toward smaller tasks but respect user choice
diff --git a/.claude/commands/opsx/sync.md b/.claude/commands/opsx/sync.md
new file mode 100644
index 0000000..1571610
--- /dev/null
+++ b/.claude/commands/opsx/sync.md
@@ -0,0 +1,134 @@
+---
+name: "OPSX: Sync"
+description: Sync delta specs from a change to main specs
+category: Workflow
+tags: [workflow, specs, experimental]
+---
+
+Sync delta specs from a change to main specs.
+
+This is an **agent-driven** operation - you will read delta specs and directly edit main specs to apply the changes. This allows intelligent merging (e.g., adding a scenario without copying the entire requirement).
+
+**Input**: Optionally specify a change name after `/opsx:sync` (e.g., `/opsx:sync add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **If no change name provided, prompt for selection**
+
+   Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
+
+   Show changes that have delta specs (under `specs/` directory).
+
+   **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
+
+2. **Find delta specs**
+
+   Look for delta spec files in `openspec/changes/<name>/specs/*/spec.md`.
+
+   Each delta spec file contains sections like:
+   - `## ADDED Requirements` - New requirements to add
+   - `## MODIFIED Requirements` - Changes to existing requirements
+   - `## REMOVED Requirements` - Requirements to remove
+   - `## RENAMED Requirements` - Requirements to rename (FROM:/TO: format)
+
+   If no delta specs found, inform user and stop.
+
+3. **For each delta spec, apply changes to main specs**
+
+   For each capability with a delta spec at `openspec/changes/<name>/specs/<capability>/spec.md`:
+
+   a. **Read the delta spec** to understand the intended changes
+
+   b. **Read the main spec** at `openspec/specs/<capability>/spec.md` (may not exist yet)
+
+   c. **Apply changes intelligently**:
+
+      **ADDED Requirements:**
+      - If requirement doesn't exist in main spec → add it
+      - If requirement already exists → update it to match (treat as implicit MODIFIED)
+
+      **MODIFIED Requirements:**
+      - Find the requirement in main spec
+      - Apply the changes - this can be:
+        - Adding new scenarios (don't need to copy existing ones)
+        - Modifying existing scenarios
+        - Changing the requirement description
+      - Preserve scenarios/content not mentioned in the delta
+
+      **REMOVED Requirements:**
+      - Remove the entire requirement block from main spec
+
+      **RENAMED Requirements:**
+      - Find the FROM requirement, rename to TO
+
+   d. **Create new main spec** if capability doesn't exist yet:
+      - Create `openspec/specs/<capability>/spec.md`
+      - Add Purpose section (can be brief, mark as TBD)
+      - Add Requirements section with the ADDED requirements
+
+4. **Show summary**
+
+   After applying all changes, summarize:
+   - Which capabilities were updated
+   - What changes were made (requirements added/modified/removed/renamed)
+
+**Delta Spec Format Reference**
+
+```markdown
+## ADDED Requirements
+
+### Requirement: New Feature
+The system SHALL do something new.
+
+#### Scenario: Basic case
+- **WHEN** user does X
+- **THEN** system does Y
+
+## MODIFIED Requirements
+
+### Requirement: Existing Feature
+#### Scenario: New scenario to add
+- **WHEN** user does A
+- **THEN** system does B
+
+## REMOVED Requirements
+
+### Requirement: Deprecated Feature
+
+## RENAMED Requirements
+
+- FROM: `### Requirement: Old Name`
+- TO: `### Requirement: New Name`
+```
+
+**Key Principle: Intelligent Merging**
+
+Unlike programmatic merging, you can apply **partial updates**:
+- To add a scenario, just include that scenario under MODIFIED - don't copy existing scenarios
+- The delta represents *intent*, not a wholesale replacement
+- Use your judgment to merge changes sensibly
+
+**Output On Success**
+
+```
+## Specs Synced: <change-name>
+
+Updated main specs:
+
+**<capability-1>**:
+- Added requirement: "New Feature"
+- Modified requirement: "Existing Feature" (added 1 scenario)
+
+**<capability-2>**:
+- Created new spec file
+- Added requirement: "Another Feature"
+
+Main specs are now updated. The change remains active - archive when implementation is complete.
+```
+
+**Guardrails**
+- Read both delta and main specs before making changes
+- Preserve existing content not mentioned in delta
+- If something is unclear, ask for clarification
+- Show what you're changing as you go
+- The operation should be idempotent - running twice should give same result
diff --git a/.claude/commands/opsx/verify.md b/.claude/commands/opsx/verify.md
new file mode 100644
index 0000000..7f403c1
--- /dev/null
+++ b/.claude/commands/opsx/verify.md
@@ -0,0 +1,164 @@
+---
+name: "OPSX: Verify"
+description: Verify implementation matches change artifacts before archiving
+category: Workflow
+tags: [workflow, verify, experimental]
+---
+
+Verify that an implementation matches the change artifacts (specs, tasks, design).
+
+**Input**: Optionally specify a change name after `/opsx:verify` (e.g., `/opsx:verify add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **If no change name provided, prompt for selection**
+
+   Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
+
+   Show changes that have implementation tasks (tasks artifact exists).
+   Include the schema used for each change if available.
+   Mark changes with incomplete tasks as "(In Progress)".
+
+   **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
+
+2. **Check status to understand the schema**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to understand:
+   - `schemaName`: The workflow being used (e.g., "spec-driven")
+   - Which artifacts exist for this change
+
+3. **Get the change directory and load artifacts**
+
+   ```bash
+   openspec instructions apply --change "<name>" --json
+   ```
+
+   This returns the change directory and `contextFiles` (artifact ID -> array of concrete file paths). Read all available artifacts from `contextFiles`.
+
+4. **Initialize verification report structure**
+
+   Create a report structure with three dimensions:
+   - **Completeness**: Track tasks and spec coverage
+   - **Correctness**: Track requirement implementation and scenario coverage
+   - **Coherence**: Track design adherence and pattern consistency
+
+   Each dimension can have CRITICAL, WARNING, or SUGGESTION issues.
+
+5. **Verify Completeness**
+
+   **Task Completion**:
+   - If `contextFiles.tasks` exists, read every file path in it
+   - Parse checkboxes: `- [ ]` (incomplete) vs `- [x]` (complete)
+   - Count complete vs total tasks
+   - If incomplete tasks exist:
+     - Add CRITICAL issue for each incomplete task
+     - Recommendation: "Complete task: <description>" or "Mark as done if already implemented"
+
+   **Spec Coverage**:
+   - If delta specs exist in `openspec/changes/<name>/specs/`:
+     - Extract all requirements (marked with "### Requirement:")
+     - For each requirement:
+       - Search codebase for keywords related to the requirement
+       - Assess if implementation likely exists
+     - If requirements appear unimplemented:
+       - Add CRITICAL issue: "Requirement not found: <requirement name>"
+       - Recommendation: "Implement requirement X: <description>"
+
+6. **Verify Correctness**
+
+   **Requirement Implementation Mapping**:
+   - For each requirement from delta specs:
+     - Search codebase for implementation evidence
+     - If found, note file paths and line ranges
+     - Assess if implementation matches requirement intent
+     - If divergence detected:
+       - Add WARNING: "Implementation may diverge from spec: <details>"
+       - Recommendation: "Review <file>:<lines> against requirement X"
+
+   **Scenario Coverage**:
+   - For each scenario in delta specs (marked with "#### Scenario:"):
+     - Check if conditions are handled in code
+     - Check if tests exist covering the scenario
+     - If scenario appears uncovered:
+       - Add WARNING: "Scenario not covered: <scenario name>"
+       - Recommendation: "Add test or implementation for scenario: <description>"
+
+7. **Verify Coherence**
+
+   **Design Adherence**:
+   - If `contextFiles.design` exists:
+     - Extract key decisions (look for sections like "Decision:", "Approach:", "Architecture:")
+     - Verify implementation follows those decisions
+     - If contradiction detected:
+       - Add WARNING: "Design decision not followed: <decision>"
+       - Recommendation: "Update implementation or revise design.md to match reality"
+   - If no design.md: Skip design adherence check, note "No design.md to verify against"
+
+   **Code Pattern Consistency**:
+   - Review new code for consistency with project patterns
+   - Check file naming, directory structure, coding style
+   - If significant deviations found:
+     - Add SUGGESTION: "Code pattern deviation: <details>"
+     - Recommendation: "Consider following project pattern: <example>"
+
+8. **Generate Verification Report**
+
+   **Summary Scorecard**:
+   ```
+   ## Verification Report: <change-name>
+
+   ### Summary
+   | Dimension    | Status           |
+   |--------------|------------------|
+   | Completeness | X/Y tasks, N reqs|
+   | Correctness  | M/N reqs covered |
+   | Coherence    | Followed/Issues  |
+   ```
+
+   **Issues by Priority**:
+
+   1. **CRITICAL** (Must fix before archive):
+      - Incomplete tasks
+      - Missing requirement implementations
+      - Each with specific, actionable recommendation
+
+   2. **WARNING** (Should fix):
+      - Spec/design divergences
+      - Missing scenario coverage
+      - Each with specific recommendation
+
+   3. **SUGGESTION** (Nice to fix):
+      - Pattern inconsistencies
+      - Minor improvements
+      - Each with specific recommendation
+
+   **Final Assessment**:
+   - If CRITICAL issues: "X critical issue(s) found. Fix before archiving."
+   - If only warnings: "No critical issues. Y warning(s) to consider. Ready for archive (with noted improvements)."
+   - If all clear: "All checks passed. Ready for archive."
+
+**Verification Heuristics**
+
+- **Completeness**: Focus on objective checklist items (checkboxes, requirements list)
+- **Correctness**: Use keyword search, file path analysis, reasonable inference - don't require perfect certainty
+- **Coherence**: Look for glaring inconsistencies, don't nitpick style
+- **False Positives**: When uncertain, prefer SUGGESTION over WARNING, WARNING over CRITICAL
+- **Actionability**: Every issue must have a specific recommendation with file/line references where applicable
+
+**Graceful Degradation**
+
+- If only tasks.md exists: verify task completion only, skip spec/design checks
+- If tasks + specs exist: verify completeness and correctness, skip design
+- If full artifacts: verify all three dimensions
+- Always note which checks were skipped and why
+
+**Output Format**
+
+Use clear markdown with:
+- Table for summary scorecard
+- Grouped lists for issues (CRITICAL/WARNING/SUGGESTION)
+- Code references in format: `file.ts:123`
+- Specific, actionable recommendations
+- No vague suggestions like "consider reviewing"
diff --git a/.claude/skills/openspec-apply-change/SKILL.md b/.claude/skills/openspec-apply-change/SKILL.md
new file mode 100644
index 0000000..70fbdb8
--- /dev/null
+++ b/.claude/skills/openspec-apply-change/SKILL.md
@@ -0,0 +1,156 @@
+---
+name: openspec-apply-change
+description: Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Implement tasks from an OpenSpec change.
+
+**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **Select the change**
+
+   If a name is provided, use it. Otherwise:
+   - Infer from conversation context if the user mentioned a change
+   - Auto-select if only one active change exists
+   - If ambiguous, run `openspec list --json` to get available changes and use the **AskUserQuestion tool** to let the user select
+
+   Always announce: "Using change: <name>" and how to override (e.g., `/opsx:apply <other>`).
+
+2. **Check status to understand the schema**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to understand:
+   - `schemaName`: The workflow being used (e.g., "spec-driven")
+   - Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
+
+3. **Get apply instructions**
+
+   ```bash
+   openspec instructions apply --change "<name>" --json
+   ```
+
+   This returns:
+   - `contextFiles`: artifact ID -> array of concrete file paths (varies by schema - could be proposal/specs/design/tasks or spec/tests/implementation/docs)
+   - Progress (total, complete, remaining)
+   - Task list with status
+   - Dynamic instruction based on current state
+
+   **Handle states:**
+   - If `state: "blocked"` (missing artifacts): show message, suggest using openspec-continue-change
+   - If `state: "all_done"`: congratulate, suggest archive
+   - Otherwise: proceed to implementation
+
+4. **Read context files**
+
+   Read every file path listed under `contextFiles` from the apply instructions output.
+   The files depend on the schema being used:
+   - **spec-driven**: proposal, specs, design, tasks
+   - Other schemas: follow the contextFiles from CLI output
+
+5. **Show current progress**
+
+   Display:
+   - Schema being used
+   - Progress: "N/M tasks complete"
+   - Remaining tasks overview
+   - Dynamic instruction from CLI
+
+6. **Implement tasks (loop until done or blocked)**
+
+   For each pending task:
+   - Show which task is being worked on
+   - Make the code changes required
+   - Keep changes minimal and focused
+   - Mark task complete in the tasks file: `- [ ]` → `- [x]`
+   - Continue to next task
+
+   **Pause if:**
+   - Task is unclear → ask for clarification
+   - Implementation reveals a design issue → suggest updating artifacts
+   - Error or blocker encountered → report and wait for guidance
+   - User interrupts
+
+7. **On completion or pause, show status**
+
+   Display:
+   - Tasks completed this session
+   - Overall progress: "N/M tasks complete"
+   - If all done: suggest archive
+   - If paused: explain why and wait for guidance
+
+**Output During Implementation**
+
+```
+## Implementing: <change-name> (schema: <schema-name>)
+
+Working on task 3/7: <task description>
+[...implementation happening...]
+✓ Task complete
+
+Working on task 4/7: <task description>
+[...implementation happening...]
+✓ Task complete
+```
+
+**Output On Completion**
+
+```
+## Implementation Complete
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Progress:** 7/7 tasks complete ✓
+
+### Completed This Session
+- [x] Task 1
+- [x] Task 2
+...
+
+All tasks complete! Ready to archive this change.
+```
+
+**Output On Pause (Issue Encountered)**
+
+```
+## Implementation Paused
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Progress:** 4/7 tasks complete
+
+### Issue Encountered
+<description of the issue>
+
+**Options:**
+1. <option 1>
+2. <option 2>
+3. Other approach
+
+What would you like to do?
+```
+
+**Guardrails**
+- Keep going through tasks until done or blocked
+- Always read context files before starting (from the apply instructions output)
+- If task is ambiguous, pause and ask before implementing
+- If implementation reveals issues, pause and suggest artifact updates
+- Keep code changes minimal and scoped to each task
+- Update task checkbox immediately after completing each task
+- Pause on errors, blockers, or unclear requirements - don't guess
+- Use contextFiles from CLI output, don't assume specific file names
+
+**Fluid Workflow Integration**
+
+This skill supports the "actions on a change" model:
+
+- **Can be invoked anytime**: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
+- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly
diff --git a/.claude/skills/openspec-archive-change/SKILL.md b/.claude/skills/openspec-archive-change/SKILL.md
new file mode 100644
index 0000000..12e2f70
--- /dev/null
+++ b/.claude/skills/openspec-archive-change/SKILL.md
@@ -0,0 +1,114 @@
+---
+name: openspec-archive-change
+description: Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Archive a completed change in the experimental workflow.
+
+**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **If no change name provided, prompt for selection**
+
+   Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
+
+   Show only active changes (not already archived).
+   Include the schema used for each change if available.
+
+   **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
+
+2. **Check artifact completion status**
+
+   Run `openspec status --change "<name>" --json` to check artifact completion.
+
+   Parse the JSON to understand:
+   - `schemaName`: The workflow being used
+   - `artifacts`: List of artifacts with their status (`done` or other)
+
+   **If any artifacts are not `done`:**
+   - Display warning listing incomplete artifacts
+   - Use **AskUserQuestion tool** to confirm user wants to proceed
+   - Proceed if user confirms
+
+3. **Check task completion status**
+
+   Read the tasks file (typically `tasks.md`) to check for incomplete tasks.
+
+   Count tasks marked with `- [ ]` (incomplete) vs `- [x]` (complete).
+
+   **If incomplete tasks found:**
+   - Display warning showing count of incomplete tasks
+   - Use **AskUserQuestion tool** to confirm user wants to proceed
+   - Proceed if user confirms
+
+   **If no tasks file exists:** Proceed without task-related warning.
+
+4. **Assess delta spec sync state**
+
+   Check for delta specs at `openspec/changes/<name>/specs/`. If none exist, proceed without sync prompt.
+
+   **If delta specs exist:**
+   - Compare each delta spec with its corresponding main spec at `openspec/specs/<capability>/spec.md`
+   - Determine what changes would be applied (adds, modifications, removals, renames)
+   - Show a combined summary before prompting
+
+   **Prompt options:**
+   - If changes needed: "Sync now (recommended)", "Archive without syncing"
+   - If already synced: "Archive now", "Sync anyway", "Cancel"
+
+   If user chooses sync, use Task tool (subagent_type: "general-purpose", prompt: "Use Skill tool to invoke openspec-sync-specs for change '<name>'. Delta spec analysis: <include the analyzed delta spec summary>"). Proceed to archive regardless of choice.
+
+5. **Perform the archive**
+
+   Create the archive directory if it doesn't exist:
+   ```bash
+   mkdir -p openspec/changes/archive
+   ```
+
+   Generate target name using current date: `YYYY-MM-DD-<change-name>`
+
+   **Check if target already exists:**
+   - If yes: Fail with error, suggest renaming existing archive or using different date
+   - If no: Move the change directory to archive
+
+   ```bash
+   mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
+   ```
+
+6. **Display summary**
+
+   Show archive completion summary including:
+   - Change name
+   - Schema that was used
+   - Archive location
+   - Whether specs were synced (if applicable)
+   - Note about any warnings (incomplete artifacts/tasks)
+
+**Output On Success**
+
+```
+## Archive Complete
+
+**Change:** <change-name>
+**Schema:** <schema-name>
+**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
+**Specs:** ✓ Synced to main specs (or "No delta specs" or "Sync skipped")
+
+All artifacts complete. All tasks complete.
+```
+
+**Guardrails**
+- Always prompt for change selection if not provided
+- Use artifact graph (openspec status --json) for completion checking
+- Don't block archive on warnings - just inform and confirm
+- Preserve .openspec.yaml when moving to archive (it moves with the directory)
+- Show clear summary of what happened
+- If sync is requested, use openspec-sync-specs approach (agent-driven)
+- If delta specs exist, always run the sync assessment and show the combined summary before prompting
diff --git a/.claude/skills/openspec-bulk-archive-change/SKILL.md b/.claude/skills/openspec-bulk-archive-change/SKILL.md
new file mode 100644
index 0000000..5be81af
--- /dev/null
+++ b/.claude/skills/openspec-bulk-archive-change/SKILL.md
@@ -0,0 +1,246 @@
+---
+name: openspec-bulk-archive-change
+description: Archive multiple completed changes at once. Use when archiving several parallel changes.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Archive multiple completed changes in a single operation.
+
+This skill allows you to batch-archive changes, handling spec conflicts intelligently by checking the codebase to determine what's actually implemented.
+
+**Input**: None required (prompts for selection)
+
+**Steps**
+
+1. **Get active changes**
+
+   Run `openspec list --json` to get all active changes.
+
+   If no active changes exist, inform user and stop.
+
+2. **Prompt for change selection**
+
+   Use **AskUserQuestion tool** with multi-select to let user choose changes:
+   - Show each change with its schema
+   - Include an option for "All changes"
+   - Allow any number of selections (1+ works, 2+ is the typical use case)
+
+   **IMPORTANT**: Do NOT auto-select. Always let the user choose.
+
+3. **Batch validation - gather status for all selected changes**
+
+   For each selected change, collect:
+
+   a. **Artifact status** - Run `openspec status --change "<name>" --json`
+      - Parse `schemaName` and `artifacts` list
+      - Note which artifacts are `done` vs other states
+
+   b. **Task completion** - Read `openspec/changes/<name>/tasks.md`
+      - Count `- [ ]` (incomplete) vs `- [x]` (complete)
+      - If no tasks file exists, note as "No tasks"
+
+   c. **Delta specs** - Check `openspec/changes/<name>/specs/` directory
+      - List which capability specs exist
+      - For each, extract requirement names (lines matching `### Requirement: <name>`)
+
+4. **Detect spec conflicts**
+
+   Build a map of `capability -> [changes that touch it]`:
+
+   ```
+   auth -> [change-a, change-b]  <- CONFLICT (2+ changes)
+   api  -> [change-c]            <- OK (only 1 change)
+   ```
+
+   A conflict exists when 2+ selected changes have delta specs for the same capability.
+
+5. **Resolve conflicts agentically**
+
+   **For each conflict**, investigate the codebase:
+
+   a. **Read the delta specs** from each conflicting change to understand what each claims to add/modify
+
+   b. **Search the codebase** for implementation evidence:
+      - Look for code implementing requirements from each delta spec
+      - Check for related files, functions, or tests
+
+   c. **Determine resolution**:
+      - If only one change is actually implemented -> sync that one's specs
+      - If both implemented -> apply in chronological order (older first, newer overwrites)
+      - If neither implemented -> skip spec sync, warn user
+
+   d. **Record resolution** for each conflict:
+      - Which change's specs to apply
+      - In what order (if both)
+      - Rationale (what was found in codebase)
+
+6. **Show consolidated status table**
+
+   Display a table summarizing all changes:
+
+   ```
+   | Change              | Artifacts | Tasks | Specs   | Conflicts | Status |
+   |---------------------|-----------|-------|---------|-----------|--------|
+   | schema-management   | Done      | 5/5   | 2 delta | None      | Ready  |
+   | project-config      | Done      | 3/3   | 1 delta | None      | Ready  |
+   | add-oauth           | Done      | 4/4   | 1 delta | auth (!)  | Ready* |
+   | add-verify-skill    | 1 left    | 2/5   | None    | None      | Warn   |
+   ```
+
+   For conflicts, show the resolution:
+   ```
+   * Conflict resolution:
+     - auth spec: Will apply add-oauth then add-jwt (both implemented, chronological order)
+   ```
+
+   For incomplete changes, show warnings:
+   ```
+   Warnings:
+   - add-verify-skill: 1 incomplete artifact, 3 incomplete tasks
+   ```
+
+7. **Confirm batch operation**
+
+   Use **AskUserQuestion tool** with a single confirmation:
+
+   - "Archive N changes?" with options based on status
+   - Options might include:
+     - "Archive all N changes"
+     - "Archive only N ready changes (skip incomplete)"
+     - "Cancel"
+
+   If there are incomplete changes, make clear they'll be archived with warnings.
+
+8. **Execute archive for each confirmed change**
+
+   Process changes in the determined order (respecting conflict resolution):
+
+   a. **Sync specs** if delta specs exist:
+      - Use the openspec-sync-specs approach (agent-driven intelligent merge)
+      - For conflicts, apply in resolved order
+      - Track if sync was done
+
+   b. **Perform the archive**:
+      ```bash
+      mkdir -p openspec/changes/archive
+      mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
+      ```
+
+   c. **Track outcome** for each change:
+      - Success: archived successfully
+      - Failed: error during archive (record error)
+      - Skipped: user chose not to archive (if applicable)
+
+9. **Display summary**
+
+   Show final results:
+
+   ```
+   ## Bulk Archive Complete
+
+   Archived 3 changes:
+   - schema-management-cli -> archive/2026-01-19-schema-management-cli/
+   - project-config -> archive/2026-01-19-project-config/
+   - add-oauth -> archive/2026-01-19-add-oauth/
+
+   Skipped 1 change:
+   - add-verify-skill (user chose not to archive incomplete)
+
+   Spec sync summary:
+   - 4 delta specs synced to main specs
+   - 1 conflict resolved (auth: applied both in chronological order)
+   ```
+
+   If any failures:
+   ```
+   Failed 1 change:
+   - some-change: Archive directory already exists
+   ```
+
+**Conflict Resolution Examples**
+
+Example 1: Only one implemented
+```
+Conflict: specs/auth/spec.md touched by [add-oauth, add-jwt]
+
+Checking add-oauth:
+- Delta adds "OAuth Provider Integration" requirement
+- Searching codebase... found src/auth/oauth.ts implementing OAuth flow
+
+Checking add-jwt:
+- Delta adds "JWT Token Handling" requirement
+- Searching codebase... no JWT implementation found
+
+Resolution: Only add-oauth is implemented. Will sync add-oauth specs only.
+```
+
+Example 2: Both implemented
+```
+Conflict: specs/api/spec.md touched by [add-rest-api, add-graphql]
+
+Checking add-rest-api (created 2026-01-10):
+- Delta adds "REST Endpoints" requirement
+- Searching codebase... found src/api/rest.ts
+
+Checking add-graphql (created 2026-01-15):
+- Delta adds "GraphQL Schema" requirement
+- Searching codebase... found src/api/graphql.ts
+
+Resolution: Both implemented. Will apply add-rest-api specs first,
+then add-graphql specs (chronological order, newer takes precedence).
+```
+
+**Output On Success**
+
+```
+## Bulk Archive Complete
+
+Archived N changes:
+- <change-1> -> archive/YYYY-MM-DD-<change-1>/
+- <change-2> -> archive/YYYY-MM-DD-<change-2>/
+
+Spec sync summary:
+- N delta specs synced to main specs
+- No conflicts (or: M conflicts resolved)
+```
+
+**Output On Partial Success**
+
+```
+## Bulk Archive Complete (partial)
+
+Archived N changes:
+- <change-1> -> archive/YYYY-MM-DD-<change-1>/
+
+Skipped M changes:
+- <change-2> (user chose not to archive incomplete)
+
+Failed K changes:
+- <change-3>: Archive directory already exists
+```
+
+**Output When No Changes**
+
+```
+## No Changes to Archive
+
+No active changes found. Create a new change to get started.
+```
+
+**Guardrails**
+- Allow any number of changes (1+ is fine, 2+ is the typical use case)
+- Always prompt for selection, never auto-select
+- Detect spec conflicts early and resolve by checking codebase
+- When both changes are implemented, apply specs in chronological order
+- Skip spec sync only when implementation is missing (warn user)
+- Show clear per-change status before confirming
+- Use single confirmation for entire batch
+- Track and report all outcomes (success/skip/fail)
+- Preserve .openspec.yaml when moving to archive
+- Archive directory target uses current date: YYYY-MM-DD-<name>
+- If archive target exists, fail that change but continue with others
diff --git a/.claude/skills/openspec-continue-change/SKILL.md b/.claude/skills/openspec-continue-change/SKILL.md
new file mode 100644
index 0000000..4f2c3dc
--- /dev/null
+++ b/.claude/skills/openspec-continue-change/SKILL.md
@@ -0,0 +1,118 @@
+---
+name: openspec-continue-change
+description: Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Continue working on a change by creating the next artifact.
+
+**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **If no change name provided, prompt for selection**
+
+   Run `openspec list --json` to get available changes sorted by most recently modified. Then use the **AskUserQuestion tool** to let the user select which change to work on.
+
+   Present the top 3-4 most recently modified changes as options, showing:
+   - Change name
+   - Schema (from `schema` field if present, otherwise "spec-driven")
+   - Status (e.g., "0/5 tasks", "complete", "no tasks")
+   - How recently it was modified (from `lastModified` field)
+
+   Mark the most recently modified change as "(Recommended)" since it's likely what the user wants to continue.
+
+   **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
+
+2. **Check current status**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to understand current state. The response includes:
+   - `schemaName`: The workflow schema being used (e.g., "spec-driven")
+   - `artifacts`: Array of artifacts with their status ("done", "ready", "blocked")
+   - `isComplete`: Boolean indicating if all artifacts are complete
+
+3. **Act based on status**:
+
+   ---
+
+   **If all artifacts are complete (`isComplete: true`)**:
+   - Congratulate the user
+   - Show final status including the schema used
+   - Suggest: "All artifacts created! You can now implement this change or archive it."
+   - STOP
+
+   ---
+
+   **If artifacts are ready to create** (status shows artifacts with `status: "ready"`):
+   - Pick the FIRST artifact with `status: "ready"` from the status output
+   - Get its instructions:
+     ```bash
+     openspec instructions <artifact-id> --change "<name>" --json
+     ```
+   - Parse the JSON. The key fields are:
+     - `context`: Project background (constraints for you - do NOT include in output)
+     - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
+     - `template`: The structure to use for your output file
+     - `instruction`: Schema-specific guidance
+     - `outputPath`: Where to write the artifact
+     - `dependencies`: Completed artifacts to read for context
+   - **Create the artifact file**:
+     - Read any completed dependency files for context
+     - Use `template` as the structure - fill in its sections
+     - Apply `context` and `rules` as constraints when writing - but do NOT copy them into the file
+     - Write to the output path specified in instructions
+   - Show what was created and what's now unlocked
+   - STOP after creating ONE artifact
+
+   ---
+
+   **If no artifacts are ready (all blocked)**:
+   - This shouldn't happen with a valid schema
+   - Show status and suggest checking for issues
+
+4. **After creating an artifact, show progress**
+   ```bash
+   openspec status --change "<name>"
+   ```
+
+**Output**
+
+After each invocation, show:
+- Which artifact was created
+- Schema workflow being used
+- Current progress (N/M complete)
+- What artifacts are now unlocked
+- Prompt: "Want to continue? Just ask me to continue or tell me what to do next."
+
+**Artifact Creation Guidelines**
+
+The artifact types and their purpose depend on the schema. Use the `instruction` field from the instructions output to understand what to create.
+
+Common artifact patterns:
+
+**spec-driven schema** (proposal → specs → design → tasks):
+- **proposal.md**: Ask user about the change if not clear. Fill in Why, What Changes, Capabilities, Impact.
+  - The Capabilities section is critical - each capability listed will need a spec file.
+- **specs/<capability>/spec.md**: Create one spec per capability listed in the proposal's Capabilities section (use the capability name, not the change name).
+- **design.md**: Document technical decisions, architecture, and implementation approach.
+- **tasks.md**: Break down implementation into checkboxed tasks.
+
+For other schemas, follow the `instruction` field from the CLI output.
+
+**Guardrails**
+- Create ONE artifact per invocation
+- Always read dependency artifacts before creating a new one
+- Never skip artifacts or create out of order
+- If context is unclear, ask the user before creating
+- Verify the artifact file exists after writing before marking progress
+- Use the schema's artifact sequence, don't assume specific artifact names
+- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
+  - Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
+  - These guide what you write, but should never appear in the output
diff --git a/.claude/skills/openspec-explore/SKILL.md b/.claude/skills/openspec-explore/SKILL.md
new file mode 100644
index 0000000..6858d3f
--- /dev/null
+++ b/.claude/skills/openspec-explore/SKILL.md
@@ -0,0 +1,288 @@
+---
+name: openspec-explore
+description: Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.
+
+**IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first and create a change proposal. You MAY create OpenSpec artifacts (proposals, designs, specs) if the user asks—that's capturing thinking, not implementing.
+
+**This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.
+
+---
+
+## The Stance
+
+- **Curious, not prescriptive** - Ask questions that emerge naturally, don't follow a script
+- **Open threads, not interrogations** - Surface multiple interesting directions and let the user follow what resonates. Don't funnel them through a single path of questions.
+- **Visual** - Use ASCII diagrams liberally when they'd help clarify thinking
+- **Adaptive** - Follow interesting threads, pivot when new information emerges
+- **Patient** - Don't rush to conclusions, let the shape of the problem emerge
+- **Grounded** - Explore the actual codebase when relevant, don't just theorize
+
+---
+
+## What You Might Do
+
+Depending on what the user brings, you might:
+
+**Explore the problem space**
+- Ask clarifying questions that emerge from what they said
+- Challenge assumptions
+- Reframe the problem
+- Find analogies
+
+**Investigate the codebase**
+- Map existing architecture relevant to the discussion
+- Find integration points
+- Identify patterns already in use
+- Surface hidden complexity
+
+**Compare options**
+- Brainstorm multiple approaches
+- Build comparison tables
+- Sketch tradeoffs
+- Recommend a path (if asked)
+
+**Visualize**
+```
+┌─────────────────────────────────────────┐
+│     Use ASCII diagrams liberally        │
+├─────────────────────────────────────────┤
+│                                         │
+│      ┌────────┐         ┌────────┐      │
+│      │ State  │────────▶│ State  │      │
+│      │   A    │         │   B    │      │
+│      └────────┘         └────────┘      │
+│                                         │
+│   System diagrams, state machines,      │
+│   data flows, architecture sketches,    │
+│   dependency graphs, comparison tables  │
+│                                         │
+└─────────────────────────────────────────┘
+```
+
+**Surface risks and unknowns**
+- Identify what could go wrong
+- Find gaps in understanding
+- Suggest spikes or investigations
+
+---
+
+## OpenSpec Awareness
+
+You have full context of the OpenSpec system. Use it naturally, don't force it.
+
+### Check for context
+
+At the start, quickly check what exists:
+```bash
+openspec list --json
+```
+
+This tells you:
+- If there are active changes
+- Their names, schemas, and status
+- What the user might be working on
+
+### When no change exists
+
+Think freely. When insights crystallize, you might offer:
+
+- "This feels solid enough to start a change. Want me to create a proposal?"
+- Or keep exploring - no pressure to formalize
+
+### When a change exists
+
+If the user mentions a change or you detect one is relevant:
+
+1. **Read existing artifacts for context**
+   - `openspec/changes/<name>/proposal.md`
+   - `openspec/changes/<name>/design.md`
+   - `openspec/changes/<name>/tasks.md`
+   - etc.
+
+2. **Reference them naturally in conversation**
+   - "Your design mentions using Redis, but we just realized SQLite fits better..."
+   - "The proposal scopes this to premium users, but we're now thinking everyone..."
+
+3. **Offer to capture when decisions are made**
+
+    | Insight Type               | Where to Capture               |
+    |----------------------------|--------------------------------|
+    | New requirement discovered | `specs/<capability>/spec.md` |
+    | Requirement changed        | `specs/<capability>/spec.md` |
+    | Design decision made       | `design.md`                  |
+    | Scope changed              | `proposal.md`                |
+    | New work identified        | `tasks.md`                   |
+    | Assumption invalidated     | Relevant artifact              |
+
+   Example offers:
+   - "That's a design decision. Capture it in design.md?"
+   - "This is a new requirement. Add it to specs?"
+   - "This changes scope. Update the proposal?"
+
+4. **The user decides** - Offer and move on. Don't pressure. Don't auto-capture.
+
+---
+
+## What You Don't Have To Do
+
+- Follow a script
+- Ask the same questions every time
+- Produce a specific artifact
+- Reach a conclusion
+- Stay on topic if a tangent is valuable
+- Be brief (this is thinking time)
+
+---
+
+## Handling Different Entry Points
+
+**User brings a vague idea:**
+```
+User: I'm thinking about adding real-time collaboration
+
+You: Real-time collab is a big space. Let me think about this...
+
+      COLLABORATION SPECTRUM
+      ════════════════════════════════════════════
+
+      Awareness          Coordination         Sync
+          │                   │                 │
+          ▼                   ▼                 ▼
+      ┌────────┐         ┌────────┐        ┌────────┐
+      │Presence│         │Cursors │        │  CRDT  │
+      │  "3    │         │ Multi  │        │Conflict│
+      │online" │         │ select │        │  free  │
+      └────────┘         └────────┘        └────────┘
+          │                   │                 │
+       trivial            moderate           complex
+
+      Where's your head at?
+```
+
+**User brings a specific problem:**
+```
+User: The auth system is a mess
+
+You: [reads codebase]
+
+     ┌─────────────────────────────────────────────┐
+     │              CURRENT AUTH FLOW              │
+     └─────────────────────────────────────────────┘
+                        │
+          ┌─────────────┼─────────────┐
+          ▼             ▼             ▼
+     ┌─────────┐  ┌─────────┐  ┌─────────┐
+     │ Google  │  │  GitHub │  │  Email  │
+     │  OAuth  │  │  OAuth  │  │  Magic  │
+     └────┬────┘  └────┬────┘  └────┬────┘
+          │             │             │
+          └─────────────┼─────────────┘
+                        ▼
+                  ┌───────────┐
+                  │  Session  │
+                  └─────┬─────┘
+                        │
+                        ▼
+                  ┌───────────┐
+                  │   Perms   │
+                  └───────────┘
+
+     I see three tangles. Which one's burning?
+```
+
+**User is stuck mid-implementation:**
+```
+User: /opsx:explore add-auth-system
+      The OAuth integration is more complex than expected
+
+You: [reads change artifacts]
+
+     You're on task 4: "Implement OAuth flow"
+
+     Let me trace what's involved...
+
+     [draws diagram, explores options, suggests paths]
+
+     Want to update the design to reflect this?
+     Or add a spike task to investigate?
+```
+
+**User wants to compare options:**
+```
+User: Should we use Postgres or SQLite?
+
+You: Generic answer is boring. What's the context?
+
+User: A CLI tool that tracks local dev environments
+
+You: That changes everything.
+
+     ┌─────────────────────────────────────────────────┐
+     │          CLI TOOL DATA STORAGE                  │
+     └─────────────────────────────────────────────────┘
+
+     Key constraints:
+     • No daemon running
+     • Must work offline
+     • Single user
+
+                  SQLite          Postgres
+     Deployment   embedded ✓      needs server ✗
+     Offline      yes ✓           no ✗
+     Single file  yes ✓           no ✗
+
+     SQLite. Not even close.
+
+     Unless... is there a sync component?
+```
+
+---
+
+## Ending Discovery
+
+There's no required ending. Discovery might:
+
+- **Flow into a proposal**: "Ready to start? I can create a change proposal."
+- **Result in artifact updates**: "Updated design.md with these decisions"
+- **Just provide clarity**: User has what they need, moves on
+- **Continue later**: "We can pick this up anytime"
+
+When it feels like things are crystallizing, you might summarize:
+
+```
+## What We Figured Out
+
+**The problem**: [crystallized understanding]
+
+**The approach**: [if one emerged]
+
+**Open questions**: [if any remain]
+
+**Next steps** (if ready):
+- Create a change proposal
+- Keep exploring: just keep talking
+```
+
+But this summary is optional. Sometimes the thinking IS the value.
+
+---
+
+## Guardrails
+
+- **Don't implement** - Never write code or implement features. Creating OpenSpec artifacts is fine, writing application code is not.
+- **Don't fake understanding** - If something is unclear, dig deeper
+- **Don't rush** - Discovery is thinking time, not task time
+- **Don't force structure** - Let patterns emerge naturally
+- **Don't auto-capture** - Offer to save insights, don't just do it
+- **Do visualize** - A good diagram is worth many paragraphs
+- **Do explore the codebase** - Ground discussions in reality
+- **Do question assumptions** - Including the user's and your own
diff --git a/.claude/skills/openspec-ff-change/SKILL.md b/.claude/skills/openspec-ff-change/SKILL.md
new file mode 100644
index 0000000..43f2632
--- /dev/null
+++ b/.claude/skills/openspec-ff-change/SKILL.md
@@ -0,0 +1,101 @@
+---
+name: openspec-ff-change
+description: Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Fast-forward through artifact creation - generate everything needed to start implementation in one go.
+
+**Input**: The user's request should include a change name (kebab-case) OR a description of what they want to build.
+
+**Steps**
+
+1. **If no clear input provided, ask what they want to build**
+
+   Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
+   > "What change do you want to work on? Describe what you want to build or fix."
+
+   From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
+
+   **IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
+
+2. **Create the change directory**
+   ```bash
+   openspec new change "<name>"
+   ```
+   This creates a scaffolded change at `openspec/changes/<name>/`.
+
+3. **Get the artifact build order**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to get:
+   - `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
+   - `artifacts`: list of all artifacts with their status and dependencies
+
+4. **Create artifacts in sequence until apply-ready**
+
+   Use the **TodoWrite tool** to track progress through the artifacts.
+
+   Loop through artifacts in dependency order (artifacts with no pending dependencies first):
+
+   a. **For each artifact that is `ready` (dependencies satisfied)**:
+      - Get instructions:
+        ```bash
+        openspec instructions <artifact-id> --change "<name>" --json
+        ```
+      - The instructions JSON includes:
+        - `context`: Project background (constraints for you - do NOT include in output)
+        - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
+        - `template`: The structure to use for your output file
+        - `instruction`: Schema-specific guidance for this artifact type
+        - `outputPath`: Where to write the artifact
+        - `dependencies`: Completed artifacts to read for context
+      - Read any completed dependency files for context
+      - Create the artifact file using `template` as the structure
+      - Apply `context` and `rules` as constraints - but do NOT copy them into the file
+      - Show brief progress: "✓ Created <artifact-id>"
+
+   b. **Continue until all `applyRequires` artifacts are complete**
+      - After creating each artifact, re-run `openspec status --change "<name>" --json`
+      - Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
+      - Stop when all `applyRequires` artifacts are done
+
+   c. **If an artifact requires user input** (unclear context):
+      - Use **AskUserQuestion tool** to clarify
+      - Then continue with creation
+
+5. **Show final status**
+   ```bash
+   openspec status --change "<name>"
+   ```
+
+**Output**
+
+After completing all artifacts, summarize:
+- Change name and location
+- List of artifacts created with brief descriptions
+- What's ready: "All artifacts created! Ready for implementation."
+- Prompt: "Run `/opsx:apply` or ask me to implement to start working on the tasks."
+
+**Artifact Creation Guidelines**
+
+- Follow the `instruction` field from `openspec instructions` for each artifact type
+- The schema defines what each artifact should contain - follow it
+- Read dependency artifacts for context before creating new ones
+- Use `template` as the structure for your output file - fill in its sections
+- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
+  - Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
+  - These guide what you write, but should never appear in the output
+
+**Guardrails**
+- Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
+- Always read dependency artifacts before creating a new one
+- If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum
+- If a change with that name already exists, suggest continuing that change instead
+- Verify each artifact file exists after writing before proceeding to next
diff --git a/.claude/skills/openspec-new-change/SKILL.md b/.claude/skills/openspec-new-change/SKILL.md
new file mode 100644
index 0000000..1af41c7
--- /dev/null
+++ b/.claude/skills/openspec-new-change/SKILL.md
@@ -0,0 +1,74 @@
+---
+name: openspec-new-change
+description: Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Start a new change using the experimental artifact-driven approach.
+
+**Input**: The user's request should include a change name (kebab-case) OR a description of what they want to build.
+
+**Steps**
+
+1. **If no clear input provided, ask what they want to build**
+
+   Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
+   > "What change do you want to work on? Describe what you want to build or fix."
+
+   From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
+
+   **IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
+
+2. **Determine the workflow schema**
+
+   Use the default schema (omit `--schema`) unless the user explicitly requests a different workflow.
+
+   **Use a different schema only if the user mentions:**
+   - A specific schema name → use `--schema <name>`
+   - "show workflows" or "what workflows" → run `openspec schemas --json` and let them choose
+
+   **Otherwise**: Omit `--schema` to use the default.
+
+3. **Create the change directory**
+   ```bash
+   openspec new change "<name>"
+   ```
+   Add `--schema <name>` only if the user requested a specific workflow.
+   This creates a scaffolded change at `openspec/changes/<name>/` with the selected schema.
+
+4. **Show the artifact status**
+   ```bash
+   openspec status --change "<name>"
+   ```
+   This shows which artifacts need to be created and which are ready (dependencies satisfied).
+
+5. **Get instructions for the first artifact**
+   The first artifact depends on the schema (e.g., `proposal` for spec-driven).
+   Check the status output to find the first artifact with status "ready".
+   ```bash
+   openspec instructions <first-artifact-id> --change "<name>"
+   ```
+   This outputs the template and context for creating the first artifact.
+
+6. **STOP and wait for user direction**
+
+**Output**
+
+After completing the steps, summarize:
+- Change name and location
+- Schema/workflow being used and its artifact sequence
+- Current status (0/N artifacts complete)
+- The template for the first artifact
+- Prompt: "Ready to create the first artifact? Just describe what this change is about and I'll draft it, or ask me to continue."
+
+**Guardrails**
+- Do NOT create any artifacts yet - just show the instructions
+- Do NOT advance beyond showing the first artifact template
+- If the name is invalid (not kebab-case), ask for a valid name
+- If a change with that name already exists, suggest continuing that change instead
+- Pass --schema if using a non-default workflow
diff --git a/.claude/skills/openspec-onboard/SKILL.md b/.claude/skills/openspec-onboard/SKILL.md
new file mode 100644
index 0000000..b6c734d
--- /dev/null
+++ b/.claude/skills/openspec-onboard/SKILL.md
@@ -0,0 +1,554 @@
+---
+name: openspec-onboard
+description: Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Guide the user through their first complete OpenSpec workflow cycle. This is a teaching experience—you'll do real work in their codebase while explaining each step.
+
+---
+
+## Preflight
+
+Before starting, check if the OpenSpec CLI is installed:
+
+```bash
+# Unix/macOS
+openspec --version 2>&1 || echo "CLI_NOT_INSTALLED"
+# Windows (PowerShell)
+# if (Get-Command openspec -ErrorAction SilentlyContinue) { openspec --version } else { echo "CLI_NOT_INSTALLED" }
+```
+
+**If CLI not installed:**
+> OpenSpec CLI is not installed. Install it first, then come back to `/opsx:onboard`.
+
+Stop here if not installed.
+
+---
+
+## Phase 1: Welcome
+
+Display:
+
+```
+## Welcome to OpenSpec!
+
+I'll walk you through a complete change cycle—from idea to implementation—using a real task in your codebase. Along the way, you'll learn the workflow by doing it.
+
+**What we'll do:**
+1. Pick a small, real task in your codebase
+2. Explore the problem briefly
+3. Create a change (the container for our work)
+4. Build the artifacts: proposal → specs → design → tasks
+5. Implement the tasks
+6. Archive the completed change
+
+**Time:** ~15-20 minutes
+
+Let's start by finding something to work on.
+```
+
+---
+
+## Phase 2: Task Selection
+
+### Codebase Analysis
+
+Scan the codebase for small improvement opportunities. Look for:
+
+1. **TODO/FIXME comments** - Search for `TODO`, `FIXME`, `HACK`, `XXX` in code files
+2. **Missing error handling** - `catch` blocks that swallow errors, risky operations without try-catch
+3. **Functions without tests** - Cross-reference `src/` with test directories
+4. **Type issues** - `any` types in TypeScript files (`: any`, `as any`)
+5. **Debug artifacts** - `console.log`, `console.debug`, `debugger` statements in non-debug code
+6. **Missing validation** - User input handlers without validation
+
+Also check recent git activity:
+```bash
+# Unix/macOS
+git log --oneline -10 2>/dev/null || echo "No git history"
+# Windows (PowerShell)
+# git log --oneline -10 2>$null; if ($LASTEXITCODE -ne 0) { echo "No git history" }
+```
+
+### Present Suggestions
+
+From your analysis, present 3-4 specific suggestions:
+
+```
+## Task Suggestions
+
+Based on scanning your codebase, here are some good starter tasks:
+
+**1. [Most promising task]**
+   Location: `src/path/to/file.ts:42`
+   Scope: ~1-2 files, ~20-30 lines
+   Why it's good: [brief reason]
+
+**2. [Second task]**
+   Location: `src/another/file.ts`
+   Scope: ~1 file, ~15 lines
+   Why it's good: [brief reason]
+
+**3. [Third task]**
+   Location: [location]
+   Scope: [estimate]
+   Why it's good: [brief reason]
+
+**4. Something else?**
+   Tell me what you'd like to work on.
+
+Which task interests you? (Pick a number or describe your own)
+```
+
+**If nothing found:** Fall back to asking what the user wants to build:
+> I didn't find obvious quick wins in your codebase. What's something small you've been meaning to add or fix?
+
+### Scope Guardrail
+
+If the user picks or describes something too large (major feature, multi-day work):
+
+```
+That's a valuable task, but it's probably larger than ideal for your first OpenSpec run-through.
+
+For learning the workflow, smaller is better—it lets you see the full cycle without getting stuck in implementation details.
+
+**Options:**
+1. **Slice it smaller** - What's the smallest useful piece of [their task]? Maybe just [specific slice]?
+2. **Pick something else** - One of the other suggestions, or a different small task?
+3. **Do it anyway** - If you really want to tackle this, we can. Just know it'll take longer.
+
+What would you prefer?
+```
+
+Let the user override if they insist—this is a soft guardrail.
+
+---
+
+## Phase 3: Explore Demo
+
+Once a task is selected, briefly demonstrate explore mode:
+
+```
+Before we create a change, let me quickly show you **explore mode**—it's how you think through problems before committing to a direction.
+```
+
+Spend 1-2 minutes investigating the relevant code:
+- Read the file(s) involved
+- Draw a quick ASCII diagram if it helps
+- Note any considerations
+
+```
+## Quick Exploration
+
+[Your brief analysis—what you found, any considerations]
+
+┌─────────────────────────────────────────┐
+│   [Optional: ASCII diagram if helpful]  │
+└─────────────────────────────────────────┘
+
+Explore mode (`/opsx:explore`) is for this kind of thinking—investigating before implementing. You can use it anytime you need to think through a problem.
+
+Now let's create a change to hold our work.
+```
+
+**PAUSE** - Wait for user acknowledgment before proceeding.
+
+---
+
+## Phase 4: Create the Change
+
+**EXPLAIN:**
+```
+## Creating a Change
+
+A "change" in OpenSpec is a container for all the thinking and planning around a piece of work. It lives in `openspec/changes/<name>/` and holds your artifacts—proposal, specs, design, tasks.
+
+Let me create one for our task.
+```
+
+**DO:** Create the change with a derived kebab-case name:
+```bash
+openspec new change "<derived-name>"
+```
+
+**SHOW:**
+```
+Created: `openspec/changes/<name>/`
+
+The folder structure:
+```
+openspec/changes/<name>/
+├── proposal.md    ← Why we're doing this (empty, we'll fill it)
+├── design.md      ← How we'll build it (empty)
+├── specs/         ← Detailed requirements (empty)
+└── tasks.md       ← Implementation checklist (empty)
+```
+
+Now let's fill in the first artifact—the proposal.
+```
+
+---
+
+## Phase 5: Proposal
+
+**EXPLAIN:**
+```
+## The Proposal
+
+The proposal captures **why** we're making this change and **what** it involves at a high level. It's the "elevator pitch" for the work.
+
+I'll draft one based on our task.
+```
+
+**DO:** Draft the proposal content (don't save yet):
+
+```
+Here's a draft proposal:
+
+---
+
+## Why
+
+[1-2 sentences explaining the problem/opportunity]
+
+## What Changes
+
+[Bullet points of what will be different]
+
+## Capabilities
+
+### New Capabilities
+- `<capability-name>`: [brief description]
+
+### Modified Capabilities
+<!-- If modifying existing behavior -->
+
+## Impact
+
+- `src/path/to/file.ts`: [what changes]
+- [other files if applicable]
+
+---
+
+Does this capture the intent? I can adjust before we save it.
+```
+
+**PAUSE** - Wait for user approval/feedback.
+
+After approval, save the proposal:
+```bash
+openspec instructions proposal --change "<name>" --json
+```
+Then write the content to `openspec/changes/<name>/proposal.md`.
+
+```
+Proposal saved. This is your "why" document—you can always come back and refine it as understanding evolves.
+
+Next up: specs.
+```
+
+---
+
+## Phase 6: Specs
+
+**EXPLAIN:**
+```
+## Specs
+
+Specs define **what** we're building in precise, testable terms. They use a requirement/scenario format that makes expected behavior crystal clear.
+
+For a small task like this, we might only need one spec file.
+```
+
+**DO:** Create the spec file:
+```bash
+# Unix/macOS
+mkdir -p openspec/changes/<name>/specs/<capability-name>
+# Windows (PowerShell)
+# New-Item -ItemType Directory -Force -Path "openspec/changes/<name>/specs/<capability-name>"
+```
+
+Draft the spec content:
+
+```
+Here's the spec:
+
+---
+
+## ADDED Requirements
+
+### Requirement: <Name>
+
+<Description of what the system should do>
+
+#### Scenario: <Scenario name>
+
+- **WHEN** <trigger condition>
+- **THEN** <expected outcome>
+- **AND** <additional outcome if needed>
+
+---
+
+This format—WHEN/THEN/AND—makes requirements testable. You can literally read them as test cases.
+```
+
+Save to `openspec/changes/<name>/specs/<capability>/spec.md`.
+
+---
+
+## Phase 7: Design
+
+**EXPLAIN:**
+```
+## Design
+
+The design captures **how** we'll build it—technical decisions, tradeoffs, approach.
+
+For small changes, this might be brief. That's fine—not every change needs deep design discussion.
+```
+
+**DO:** Draft design.md:
+
+```
+Here's the design:
+
+---
+
+## Context
+
+[Brief context about the current state]
+
+## Goals / Non-Goals
+
+**Goals:**
+- [What we're trying to achieve]
+
+**Non-Goals:**
+- [What's explicitly out of scope]
+
+## Decisions
+
+### Decision 1: [Key decision]
+
+[Explanation of approach and rationale]
+
+---
+
+For a small task, this captures the key decisions without over-engineering.
+```
+
+Save to `openspec/changes/<name>/design.md`.
+
+---
+
+## Phase 8: Tasks
+
+**EXPLAIN:**
+```
+## Tasks
+
+Finally, we break the work into implementation tasks—checkboxes that drive the apply phase.
+
+These should be small, clear, and in logical order.
+```
+
+**DO:** Generate tasks based on specs and design:
+
+```
+Here are the implementation tasks:
+
+---
+
+## 1. [Category or file]
+
+- [ ] 1.1 [Specific task]
+- [ ] 1.2 [Specific task]
+
+## 2. Verify
+
+- [ ] 2.1 [Verification step]
+
+---
+
+Each checkbox becomes a unit of work in the apply phase. Ready to implement?
+```
+
+**PAUSE** - Wait for user to confirm they're ready to implement.
+
+Save to `openspec/changes/<name>/tasks.md`.
+
+---
+
+## Phase 9: Apply (Implementation)
+
+**EXPLAIN:**
+```
+## Implementation
+
+Now we implement each task, checking them off as we go. I'll announce each one and occasionally note how the specs/design informed the approach.
+```
+
+**DO:** For each task:
+
+1. Announce: "Working on task N: [description]"
+2. Implement the change in the codebase
+3. Reference specs/design naturally: "The spec says X, so I'm doing Y"
+4. Mark complete in tasks.md: `- [ ]` → `- [x]`
+5. Brief status: "✓ Task N complete"
+
+Keep narration light—don't over-explain every line of code.
+
+After all tasks:
+
+```
+## Implementation Complete
+
+All tasks done:
+- [x] Task 1
+- [x] Task 2
+- [x] ...
+
+The change is implemented! One more step—let's archive it.
+```
+
+---
+
+## Phase 10: Archive
+
+**EXPLAIN:**
+```
+## Archiving
+
+When a change is complete, we archive it. This moves it from `openspec/changes/` to `openspec/changes/archive/YYYY-MM-DD-<name>/`.
+
+Archived changes become your project's decision history—you can always find them later to understand why something was built a certain way.
+```
+
+**DO:**
+```bash
+openspec archive "<name>"
+```
+
+**SHOW:**
+```
+Archived to: `openspec/changes/archive/YYYY-MM-DD-<name>/`
+
+The change is now part of your project's history. The code is in your codebase, the decision record is preserved.
+```
+
+---
+
+## Phase 11: Recap & Next Steps
+
+```
+## Congratulations!
+
+You just completed a full OpenSpec cycle:
+
+1. **Explore** - Thought through the problem
+2. **New** - Created a change container
+3. **Proposal** - Captured WHY
+4. **Specs** - Defined WHAT in detail
+5. **Design** - Decided HOW
+6. **Tasks** - Broke it into steps
+7. **Apply** - Implemented the work
+8. **Archive** - Preserved the record
+
+This same rhythm works for any size change—a small fix or a major feature.
+
+---
+
+## Command Reference
+
+**Core workflow:**
+
+ | Command           | What it does                               |
+ |-------------------|--------------------------------------------|
+ | `/opsx:propose` | Create a change and generate all artifacts |
+ | `/opsx:explore` | Think through problems before/during work  |
+ | `/opsx:apply`   | Implement tasks from a change              |
+ | `/opsx:archive` | Archive a completed change                 |
+
+**Additional commands:**
+
+ | Command            | What it does                                             |
+ |--------------------|----------------------------------------------------------|
+ | `/opsx:new`      | Start a new change, step through artifacts one at a time |
+ | `/opsx:continue` | Continue working on an existing change                   |
+ | `/opsx:ff`       | Fast-forward: create all artifacts at once               |
+ | `/opsx:verify`   | Verify implementation matches artifacts                  |
+
+---
+
+## What's Next?
+
+Try `/opsx:propose` on something you actually want to build. You've got the rhythm now!
+```
+
+---
+
+## Graceful Exit Handling
+
+### User wants to stop mid-way
+
+If the user says they need to stop, want to pause, or seem disengaged:
+
+```
+No problem! Your change is saved at `openspec/changes/<name>/`.
+
+To pick up where we left off later:
+- `/opsx:continue <name>` - Resume artifact creation
+- `/opsx:apply <name>` - Jump to implementation (if tasks exist)
+
+The work won't be lost. Come back whenever you're ready.
+```
+
+Exit gracefully without pressure.
+
+### User just wants command reference
+
+If the user says they just want to see the commands or skip the tutorial:
+
+```
+## OpenSpec Quick Reference
+
+**Core workflow:**
+
+ | Command                  | What it does                               |
+ |--------------------------|--------------------------------------------|
+ | `/opsx:propose <name>` | Create a change and generate all artifacts |
+ | `/opsx:explore`        | Think through problems (no code changes)   |
+ | `/opsx:apply <name>`   | Implement tasks                            |
+ | `/opsx:archive <name>` | Archive when done                          |
+
+**Additional commands:**
+
+ | Command                   | What it does                        |
+ |---------------------------|-------------------------------------|
+ | `/opsx:new <name>`      | Start a new change, step by step    |
+ | `/opsx:continue <name>` | Continue an existing change         |
+ | `/opsx:ff <name>`       | Fast-forward: all artifacts at once |
+ | `/opsx:verify <name>`   | Verify implementation               |
+
+Try `/opsx:propose` to start your first change.
+```
+
+Exit gracefully.
+
+---
+
+## Guardrails
+
+- **Follow the EXPLAIN → DO → SHOW → PAUSE pattern** at key transitions (after explore, after proposal draft, after tasks, after archive)
+- **Keep narration light** during implementation—teach without lecturing
+- **Don't skip phases** even if the change is small—the goal is teaching the workflow
+- **Pause for acknowledgment** at marked points, but don't over-pause
+- **Handle exits gracefully**—never pressure the user to continue
+- **Use real codebase tasks**—don't simulate or use fake examples
+- **Adjust scope gently**—guide toward smaller tasks but respect user choice
diff --git a/.claude/skills/openspec-sync-specs/SKILL.md b/.claude/skills/openspec-sync-specs/SKILL.md
new file mode 100644
index 0000000..f2ed9ec
--- /dev/null
+++ b/.claude/skills/openspec-sync-specs/SKILL.md
@@ -0,0 +1,138 @@
+---
+name: openspec-sync-specs
+description: Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Sync delta specs from a change to main specs.
+
+This is an **agent-driven** operation - you will read delta specs and directly edit main specs to apply the changes. This allows intelligent merging (e.g., adding a scenario without copying the entire requirement).
+
+**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **If no change name provided, prompt for selection**
+
+   Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
+
+   Show changes that have delta specs (under `specs/` directory).
+
+   **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
+
+2. **Find delta specs**
+
+   Look for delta spec files in `openspec/changes/<name>/specs/*/spec.md`.
+
+   Each delta spec file contains sections like:
+   - `## ADDED Requirements` - New requirements to add
+   - `## MODIFIED Requirements` - Changes to existing requirements
+   - `## REMOVED Requirements` - Requirements to remove
+   - `## RENAMED Requirements` - Requirements to rename (FROM:/TO: format)
+
+   If no delta specs found, inform user and stop.
+
+3. **For each delta spec, apply changes to main specs**
+
+   For each capability with a delta spec at `openspec/changes/<name>/specs/<capability>/spec.md`:
+
+   a. **Read the delta spec** to understand the intended changes
+
+   b. **Read the main spec** at `openspec/specs/<capability>/spec.md` (may not exist yet)
+
+   c. **Apply changes intelligently**:
+
+      **ADDED Requirements:**
+      - If requirement doesn't exist in main spec → add it
+      - If requirement already exists → update it to match (treat as implicit MODIFIED)
+
+      **MODIFIED Requirements:**
+      - Find the requirement in main spec
+      - Apply the changes - this can be:
+        - Adding new scenarios (don't need to copy existing ones)
+        - Modifying existing scenarios
+        - Changing the requirement description
+      - Preserve scenarios/content not mentioned in the delta
+
+      **REMOVED Requirements:**
+      - Remove the entire requirement block from main spec
+
+      **RENAMED Requirements:**
+      - Find the FROM requirement, rename to TO
+
+   d. **Create new main spec** if capability doesn't exist yet:
+      - Create `openspec/specs/<capability>/spec.md`
+      - Add Purpose section (can be brief, mark as TBD)
+      - Add Requirements section with the ADDED requirements
+
+4. **Show summary**
+
+   After applying all changes, summarize:
+   - Which capabilities were updated
+   - What changes were made (requirements added/modified/removed/renamed)
+
+**Delta Spec Format Reference**
+
+```markdown
+## ADDED Requirements
+
+### Requirement: New Feature
+The system SHALL do something new.
+
+#### Scenario: Basic case
+- **WHEN** user does X
+- **THEN** system does Y
+
+## MODIFIED Requirements
+
+### Requirement: Existing Feature
+#### Scenario: New scenario to add
+- **WHEN** user does A
+- **THEN** system does B
+
+## REMOVED Requirements
+
+### Requirement: Deprecated Feature
+
+## RENAMED Requirements
+
+- FROM: `### Requirement: Old Name`
+- TO: `### Requirement: New Name`
+```
+
+**Key Principle: Intelligent Merging**
+
+Unlike programmatic merging, you can apply **partial updates**:
+- To add a scenario, just include that scenario under MODIFIED - don't copy existing scenarios
+- The delta represents *intent*, not a wholesale replacement
+- Use your judgment to merge changes sensibly
+
+**Output On Success**
+
+```
+## Specs Synced: <change-name>
+
+Updated main specs:
+
+**<capability-1>**:
+- Added requirement: "New Feature"
+- Modified requirement: "Existing Feature" (added 1 scenario)
+
+**<capability-2>**:
+- Created new spec file
+- Added requirement: "Another Feature"
+
+Main specs are now updated. The change remains active - archive when implementation is complete.
+```
+
+**Guardrails**
+- Read both delta and main specs before making changes
+- Preserve existing content not mentioned in delta
+- If something is unclear, ask for clarification
+- Show what you're changing as you go
+- The operation should be idempotent - running twice should give same result
diff --git a/.claude/skills/openspec-verify-change/SKILL.md b/.claude/skills/openspec-verify-change/SKILL.md
new file mode 100644
index 0000000..00d0532
--- /dev/null
+++ b/.claude/skills/openspec-verify-change/SKILL.md
@@ -0,0 +1,168 @@
+---
+name: openspec-verify-change
+description: Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
+license: MIT
+compatibility: Requires openspec CLI.
+metadata:
+  author: openspec
+  version: "1.0"
+  generatedBy: "1.3.1"
+---
+
+Verify that an implementation matches the change artifacts (specs, tasks, design).
+
+**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
+
+**Steps**
+
+1. **If no change name provided, prompt for selection**
+
+   Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
+
+   Show changes that have implementation tasks (tasks artifact exists).
+   Include the schema used for each change if available.
+   Mark changes with incomplete tasks as "(In Progress)".
+
+   **IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
+
+2. **Check status to understand the schema**
+   ```bash
+   openspec status --change "<name>" --json
+   ```
+   Parse the JSON to understand:
+   - `schemaName`: The workflow being used (e.g., "spec-driven")
+   - Which artifacts exist for this change
+
+3. **Get the change directory and load artifacts**
+
+   ```bash
+   openspec instructions apply --change "<name>" --json
+   ```
+
+   This returns the change directory and `contextFiles` (artifact ID -> array of concrete file paths). Read all available artifacts from `contextFiles`.
+
+4. **Initialize verification report structure**
+
+   Create a report structure with three dimensions:
+   - **Completeness**: Track tasks and spec coverage
+   - **Correctness**: Track requirement implementation and scenario coverage
+   - **Coherence**: Track design adherence and pattern consistency
+
+   Each dimension can have CRITICAL, WARNING, or SUGGESTION issues.
+
+5. **Verify Completeness**
+
+   **Task Completion**:
+   - If `contextFiles.tasks` exists, read every file path in it
+   - Parse checkboxes: `- [ ]` (incomplete) vs `- [x]` (complete)
+   - Count complete vs total tasks
+   - If incomplete tasks exist:
+     - Add CRITICAL issue for each incomplete task
+     - Recommendation: "Complete task: <description>" or "Mark as done if already implemented"
+
+   **Spec Coverage**:
+   - If delta specs exist in `openspec/changes/<name>/specs/`:
+     - Extract all requirements (marked with "### Requirement:")
+     - For each requirement:
+       - Search codebase for keywords related to the requirement
+       - Assess if implementation likely exists
+     - If requirements appear unimplemented:
+       - Add CRITICAL issue: "Requirement not found: <requirement name>"
+       - Recommendation: "Implement requirement X: <description>"
+
+6. **Verify Correctness**
+
+   **Requirement Implementation Mapping**:
+   - For each requirement from delta specs:
+     - Search codebase for implementation evidence
+     - If found, note file paths and line ranges
+     - Assess if implementation matches requirement intent
+     - If divergence detected:
+       - Add WARNING: "Implementation may diverge from spec: <details>"
+       - Recommendation: "Review <file>:<lines> against requirement X"
+
+   **Scenario Coverage**:
+   - For each scenario in delta specs (marked with "#### Scenario:"):
+     - Check if conditions are handled in code
+     - Check if tests exist covering the scenario
+     - If scenario appears uncovered:
+       - Add WARNING: "Scenario not covered: <scenario name>"
+       - Recommendation: "Add test or implementation for scenario: <description>"
+
+7. **Verify Coherence**
+
+   **Design Adherence**:
+   - If `contextFiles.design` exists:
+     - Extract key decisions (look for sections like "Decision:", "Approach:", "Architecture:")
+     - Verify implementation follows those decisions
+     - If contradiction detected:
+       - Add WARNING: "Design decision not followed: <decision>"
+       - Recommendation: "Update implementation or revise design.md to match reality"
+   - If no design.md: Skip design adherence check, note "No design.md to verify against"
+
+   **Code Pattern Consistency**:
+   - Review new code for consistency with project patterns
+   - Check file naming, directory structure, coding style
+   - If significant deviations found:
+     - Add SUGGESTION: "Code pattern deviation: <details>"
+     - Recommendation: "Consider following project pattern: <example>"
+
+8. **Generate Verification Report**
+
+   **Summary Scorecard**:
+   ```
+   ## Verification Report: <change-name>
+
+   ### Summary
+   | Dimension    | Status           |
+   |--------------|------------------|
+   | Completeness | X/Y tasks, N reqs|
+   | Correctness  | M/N reqs covered |
+   | Coherence    | Followed/Issues  |
+   ```
+
+   **Issues by Priority**:
+
+   1. **CRITICAL** (Must fix before archive):
+      - Incomplete tasks
+      - Missing requirement implementations
+      - Each with specific, actionable recommendation
+
+   2. **WARNING** (Should fix):
+      - Spec/design divergences
+      - Missing scenario coverage
+      - Each with specific recommendation
+
+   3. **SUGGESTION** (Nice to fix):
+      - Pattern inconsistencies
+      - Minor improvements
+      - Each with specific recommendation
+
+   **Final Assessment**:
+   - If CRITICAL issues: "X critical issue(s) found. Fix before archiving."
+   - If only warnings: "No critical issues. Y warning(s) to consider. Ready for archive (with noted improvements)."
+   - If all clear: "All checks passed. Ready for archive."
+
+**Verification Heuristics**
+
+- **Completeness**: Focus on objective checklist items (checkboxes, requirements list)
+- **Correctness**: Use keyword search, file path analysis, reasonable inference - don't require perfect certainty
+- **Coherence**: Look for glaring inconsistencies, don't nitpick style
+- **False Positives**: When uncertain, prefer SUGGESTION over WARNING, WARNING over CRITICAL
+- **Actionability**: Every issue must have a specific recommendation with file/line references where applicable
+
+**Graceful Degradation**
+
+- If only tasks.md exists: verify task completion only, skip spec/design checks
+- If tasks + specs exist: verify completeness and correctness, skip design
+- If full artifacts: verify all three dimensions
+- Always note which checks were skipped and why
+
+**Output Format**
+
+Use clear markdown with:
+- Table for summary scorecard
+- Grouped lists for issues (CRITICAL/WARNING/SUGGESTION)
+- Code references in format: `file.ts:123`
+- Specific, actionable recommendations
+- No vague suggestions like "consider reviewing"
diff --git a/openspec/config.yaml b/openspec/config.yaml
new file mode 100644
index 0000000..392946c
--- /dev/null
+++ b/openspec/config.yaml
@@ -0,0 +1,20 @@
+schema: spec-driven
+
+# Project context (optional)
+# This is shown to AI when creating artifacts.
+# Add your tech stack, conventions, style guides, domain knowledge, etc.
+# Example:
+#   context: |
+#     Tech stack: TypeScript, React, Node.js
+#     We use conventional commits
+#     Domain: e-commerce platform
+
+# Per-artifact rules (optional)
+# Add custom rules for specific artifacts.
+# Example:
+#   rules:
+#     proposal:
+#       - Keep proposals under 500 words
+#       - Always include a "Non-goals" section
+#     tasks:
+#       - Break tasks into chunks of max 2 hours

From 86b67c505359ab3dc19fcf6caf90831ca8b848ab Mon Sep 17 00:00:00 2001
From: John Grimes <John.Grimes@csiro.au>
Date: Fri, 29 May 2026 04:35:10 +1000
Subject: [PATCH 2/6] Adopt project constitution

---
 .claude/CLAUDE.md | 87 +++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 85 insertions(+), 2 deletions(-)

diff --git a/.claude/CLAUDE.md b/.claude/CLAUDE.md
index be65129..56e0e6e 100644
--- a/.claude/CLAUDE.md
+++ b/.claude/CLAUDE.md
@@ -1,5 +1,86 @@
 # Project instructions
 
+## Constitution
+
+### sof-mssql Constitution
+
+#### Core Principles
+
+##### I. Specification conformance (NON-NEGOTIABLE)
+
+Every transpilation feature MUST conform to the [SQL on FHIR v2
+specification](https://sql-on-fhir.org/ig/2.0.0/). Conformance is proven, not
+asserted: the upstream `sqlonfhir` test submodule is the source of truth, and
+all in-scope (non-`#experimental`) tests MUST pass before a change merges. A
+feature that diverges from the specification MUST either be tagged
+`#experimental` with a documented reason, or not ship. New behaviour MUST cite
+the relevant section of the specification.
+
+_Rationale: the project's entire value is being a faithful SQL on FHIR runner.
+Silent divergence from the spec produces wrong analytical results that
+downstream users cannot detect._
+
+##### II. Valid, executable T-SQL
+
+All generated SQL MUST be valid, executable T-SQL for Microsoft SQL Server 2017
+and later. Output MUST NOT rely on engine-specific extensions beyond that
+baseline, MUST bracket-quote identifiers where required, and MUST handle empty
+collections as SQL `NULL` per the specification's data-type mapping. Generated
+SQL is an external contract: it MUST be verified against a real SQL Server
+instance, not merely inspected as a string.
+
+_Rationale: a query that parses in TypeScript but fails or silently
+mis-executes on SQL Server is a defect the library exists to prevent._
+
+##### III. Test-first (NON-NEGOTIABLE)
+
+Tests MUST be written before implementation. For every feature or bug fix, a
+failing test that defines the expected behaviour comes first; implementation
+follows only to make it pass. The Red-Green-Refactor cycle is strictly
+enforced. Bug fixes MUST include a regression test that fails without the fix.
+No change merges without its behaviour expressed as an executable test.
+
+##### IV. Trusted boundaries through validated input
+
+External input - ViewDefinition JSON, CLI arguments, NDJSON resources - MUST be
+accepted as `unknown` and narrowed through runtime type predicates
+(`data is Type`) before use. Blind type assertions (`as SomeType`) on
+unvalidated data are forbidden. Invalid input MUST be rejected with a meaningful
+error that references the offending ViewDefinition element.
+
+_Rationale: the library transpiles attacker- or user-controlled documents into
+SQL; trusting unvalidated structure invites both crashes and malformed output._
+
+##### V. Functional, composable design
+
+Behaviour MUST be expressed through small, single-responsibility, pure
+functions composed together, favouring immutable data. Classes are permitted
+only where they provide clear encapsulation of genuine state (e.g. the public
+`SqlOnFhir` facade); they MUST NOT be used as namespaces for otherwise-stateless
+logic. Each module owns one concern - parsing, FHIRPath translation, T-SQL
+generation, loading - and exposes only what callers need.
+
+#### Quality gates
+
+Before any change is considered complete it MUST pass, locally and in CI:
+
+- A clean `npm run build`.
+- The full test suite with coverage via `npm run test:coverage`, run with the
+  database environment sourced (`set -a && source .env && set +a`).
+- `npm run lint` with no errors or warnings.
+- `npm run format:check` with no formatting differences.
+
+These gates are not advisory. A change that cannot pass them is not done,
+regardless of how complete the implementation appears.
+
+#### Amendment and review
+
+A pull request MAY be rejected by citing the specific principle it violates
+(e.g. "violates Principle II - emits a SQL Server 2022-only function"). The
+constitution governs reviews and is the tie-breaker when guidance conflicts.
+Amendments are made by editing this section directly and explaining the change
+in the commit message.
+
 ## Getting started
 
 Before starting any work on this project, always read the CONTRIBUTING.md file to understand the project's contribution guidelines and requirements.
@@ -44,15 +125,17 @@ When checking files for problems using the `mcp__intellij__get_file_problems` to
 - Include both SonarQube and IDE warnings to ensure comprehensive code quality checks
 
 Example:
+
 ```typescript
 mcp__intellij__get_file_problems({
   filePath: "src/parser.ts",
   projectPath: "/Users/gri306/Code/sof-mssql",
-  errorsOnly: false  // IMPORTANT: Include warnings
-})
+  errorsOnly: false, // IMPORTANT: Include warnings
+});
 ```
 
 Warnings often catch important issues such as:
+
 - Using deprecated APIs (e.g., `isNaN` vs `Number.isNaN`)
 - Type validation requiring specific error types (e.g., `TypeError` for type checks)
 - Complex regex patterns that should be simplified

From 8694a8593c8dee98565237581054f1e3d683a053 Mon Sep 17 00:00:00 2001
From: John Grimes <John.Grimes@csiro.au>
Date: Fri, 29 May 2026 04:46:22 +1000
Subject: [PATCH 3/6] Add OpenSpec change for %rowIndex environment variable

Scaffolds the implement-row-index change with proposal, spec, design,
and tasks for resolving the SQL on FHIR %rowIndex environment variable
to a 0-based T-SQL integer across forEach, forEachOrNull, repeat, and
unionAll, so the nine in-scope row_index tests can pass.

Re #11
---
 .../implement-row-index/.openspec.yaml        |   2 +
 .../changes/implement-row-index/design.md     | 170 ++++++++++++++++++
 .../changes/implement-row-index/proposal.md   |  56 ++++++
 .../specs/row-index-variable/spec.md          | 109 +++++++++++
 openspec/changes/implement-row-index/tasks.md |  34 ++++
 5 files changed, 371 insertions(+)
 create mode 100644 openspec/changes/implement-row-index/.openspec.yaml
 create mode 100644 openspec/changes/implement-row-index/design.md
 create mode 100644 openspec/changes/implement-row-index/proposal.md
 create mode 100644 openspec/changes/implement-row-index/specs/row-index-variable/spec.md
 create mode 100644 openspec/changes/implement-row-index/tasks.md

diff --git a/openspec/changes/implement-row-index/.openspec.yaml b/openspec/changes/implement-row-index/.openspec.yaml
new file mode 100644
index 0000000..352690f
--- /dev/null
+++ b/openspec/changes/implement-row-index/.openspec.yaml
@@ -0,0 +1,2 @@
+schema: spec-driven
+created: 2026-05-28
diff --git a/openspec/changes/implement-row-index/design.md b/openspec/changes/implement-row-index/design.md
new file mode 100644
index 0000000..d5f31d9
--- /dev/null
+++ b/openspec/changes/implement-row-index/design.md
@@ -0,0 +1,170 @@
+## Context
+
+The transpiler turns ViewDefinition column `path` expressions into T-SQL via a
+FHIRPath visitor (`src/fhirpath/visitor.ts`) driven by a `TranspilerContext`,
+and a tree walker (`src/queryGenerator/treeWalker/`) that emits the surrounding
+`SELECT` / `APPLY` / CTE structure. Iteration constructs already thread context
+to the visitor:
+
+- `forEach` / `forEachOrNull` (`operators/forEach.ts`) emit `CROSS APPLY` /
+  `OUTER APPLY OPENJSON(...)` and set `currentForEachAlias`; the iterated
+  element's 0-based position is the `OPENJSON` `[key]` column, already exposed
+  to `$index` via `visitIndexInvocation` (`visitor.ts:398`).
+- `repeat` (`operators/repeat.ts`, `cteTemplates.ts`) emits a recursive CTE that
+  accumulates a `.`-joined `__path` of element keys for stable identity, and
+  also sets `currentForEachAlias` to the CTE alias.
+- `unionAll` (`operators/unionAll.ts`) walks every branch in the **same** parent
+  context (`unionAll.ts:73`), so a branch carries whatever iteration context
+  encloses the `unionAll`.
+
+Today `%rowIndex` is unhandled: `visitExternalConstant` (`visitor.ts:444`)
+throws `Constant '%rowIndex' is not defined` for any name not present in the
+ViewDefinition's `constant` list. The nine in-scope tests in
+`sqlonfhir/tests/row_index.json` therefore fail. See `proposal.md` for
+motivation and `specs/row-index-variable/spec.md` for the normative behaviour.
+
+## Goals / Non-Goals
+
+**Goals:**
+
+- Resolve `%rowIndex` to the 0-based index of the innermost active iteration
+  (`forEach`, `forEachOrNull`, `repeat`), and to `0` when no iteration is
+  active, producing valid T-SQL `INT`.
+- Make all nine in-scope `row_index.json` tests pass without tagging any
+  `#experimental` (constitution Principle I).
+- Keep the change additive and behaviour-preserving for every other test.
+
+**Non-Goals:**
+
+- Changing the behaviour of the `$index` FHIRPath built-in
+  (`visitIndexInvocation`). It overlaps conceptually but is out of scope here;
+  see Open Questions.
+- Supporting `%rowIndex` anywhere other than column `path` expressions (the spec
+  scopes it to iteration over `select` columns).
+- General-purpose user-defined environment variables beyond the existing
+  `constant` mechanism.
+
+## Decisions
+
+### Decision 1: Resolve `%rowIndex` from a dedicated context field
+
+Add an optional `rowIndexExpr?: string` to `TranspilerContext`. In
+`visitExternalConstant`, special-case the name `rowIndex` **before** the
+constants lookup and the "not defined" error, returning
+`this.context.rowIndexExpr ?? "0"`.
+
+Each iteration operator populates `rowIndexExpr` with the SQL expression that
+yields that iteration's 0-based index. The resolved expression is an integer, so
+columns typed `integer` cast cleanly and `%rowIndex` is correct even when used
+without an explicit type.
+
+_Why a dedicated field rather than reusing `currentForEachAlias`._ For `forEach`
+the index is `currentForEachAlias.[key]`, but `repeat` sets
+`currentForEachAlias` to a **CTE** alias that has no `[key]` column and needs a
+different, traversal-ordered expression. A single `[key]`-based rule cannot
+serve both. A dedicated field lets each operator supply the right expression and
+decouples `%rowIndex` from the `$index` logic.
+
+_Alternative considered._ Compute the expression inside the visitor from
+`currentForEachAlias`. Rejected: the visitor cannot distinguish a `forEach`
+alias from a `repeat` CTE alias, and does not know the partition keys needed for
+the `repeat` window function.
+
+### Decision 2: `forEach` / `forEachOrNull` set `rowIndexExpr` from `[key]`
+
+`buildInnerCtx` sets `rowIndexExpr = COALESCE(CAST(<alias>.[key] AS INT), 0)`.
+
+The `CAST` makes the `NVARCHAR` `[key]` an `INT`. The `COALESCE(..., 0)` covers
+`forEachOrNull` over an empty collection: `OUTER APPLY` yields a single row with
+a `NULL` `[key]`, and the spec requires `%rowIndex = 0` for that null-padded row
+(`spec.md` scenario "forEachOrNull on an empty collection reports zero").
+
+Nested `forEach` works for free: each level's `buildInnerCtx` overwrites
+`rowIndexExpr` with its own alias, and a column resolves against the context of
+its own `select` level.
+
+### Decision 3: `repeat` sets `rowIndexExpr` to a traversal-ordered row number
+
+`%rowIndex` inside `repeat` must be the position within the flattened
+depth-first (pre-order) traversal - `0, 1, 2, 3` for items `1, 1.1, 1.2, 2`
+(`spec.md` scenario "repeat reports flattened traversal position").
+
+`buildRepeatInnerCtx` sets:
+
+```
+rowIndexExpr = (ROW_NUMBER() OVER (PARTITION BY <ancestor partition keys>
+                                   ORDER BY <cteAlias>.__order) - 1)
+```
+
+where `<ancestor partition keys>` are `ctx.partitionKeys` from before the repeat
+key is appended (so each resource - and each enclosing `forEach` element - gets
+its own 0-based sequence). The window function lives in the outer `SELECT`,
+which already `INNER JOIN`s the CTE, so the reference is in scope.
+
+To order pre-order correctly, extend the recursive CTE
+(`cteTemplates.ts`) to accumulate an ordering key `__order` exactly as it builds
+`__path`, but with each segment's `[key]` zero-padded to a fixed width
+(e.g. `RIGHT('0000000000' + CAST(... AS NVARCHAR(10)), 10)`). Lexical ordering of
+the padded, `.`-joined key path is then equivalent to numeric pre-order.
+
+_Alternative considered._ Order by the existing `__path` directly. Rejected:
+`__path` zero-pads nothing, so lexical order breaks once any level has ten or
+more elements (`"10" < "2"`). The test data stays single-digit, but ordering on
+unpadded keys is a latent conformance bug (Principle I) for no real saving.
+
+_Alternative considered._ Compute the row number inside the CTE. Rejected:
+`ROW_NUMBER()` cannot reference the full recursive result from within the
+recursive member; the outer query is the correct place.
+
+### Decision 4: `unionAll` needs no change
+
+`walkUnionAll` already walks each branch in the enclosing context
+(`unionAll.ts:73`). A branch that introduces its own `forEach` / `repeat`
+overwrites `rowIndexExpr` within its own walk; a branch with no iteration keeps
+the enclosing `rowIndexExpr` (the enclosing `forEach` index, or unset → `0` at
+top level). Because the `CROSS APPLY (… UNION ALL …)` derived table is
+correlated, an inherited `forEach` alias remains in scope inside the branch.
+This delivers all three `unionAll` scenarios in `spec.md` with no operator
+change.
+
+### Decision 5: Top level resolves to `0`
+
+No operator sets `rowIndexExpr` at the resource root, so `visitExternalConstant`
+returns the `"0"` fallback - one value per resource row, matching the top-level
+scenario.
+
+## Risks / Trade-offs
+
+- **Recursive CTE output order is not guaranteed by SQL Server** → the
+  `%rowIndex` window function uses an explicit `ORDER BY <cteAlias>.__order`
+  rather than relying on physical row order.
+- **Multi-digit array indices breaking lexical pre-order** → mitigated by
+  zero-padding each key segment in `__order` (Decision 3).
+- **Generated SQL must execute, not merely parse** (Principle II) → verify the
+  `ROW_NUMBER() OVER (…)` column, the `OUTER APPLY` `COALESCE`, and the
+  `unionAll`-inherited alias references against a real SQL Server via the test
+  suite, not by string inspection.
+- **Over-broad special-casing** → only the exact name `rowIndex` is intercepted;
+  every other unknown `%name` still raises the existing "not defined" error, and
+  a user `constant` literally named `rowIndex` is intentionally shadowed (the
+  spec reserves the name).
+- **Padding width assumption** → a fixed 10-character pad assumes no single
+  collection level exceeds `10^10` elements, which is safe for FHIR resources.
+
+## Migration Plan
+
+Additive change; no data or API migration. Rollback is a straight revert of the
+commit. Validation is the existing quality gate run with the database sourced:
+`set -a && source .env && set +a && npm run test:coverage`, plus `npm run lint`,
+`npm run format:check`, and `npm run build`.
+
+## Open Questions
+
+- Should `$index` (`visitIndexInvocation`) be unified with `%rowIndex` by
+  routing it through `rowIndexExpr`? It would fix `$index` inside `repeat` (which
+  currently emits a non-existent `<cteAlias>.[key]`) and remove duplication, but
+  risks changing untested `$index` behaviour. Deferred unless a failing test
+  demands it.
+- The SoF specification text on `%rowIndex` within `repeat` is light; this design
+  treats the `row_index.json` expectations (depth-first pre-order) as the source
+  of truth per the constitution.
diff --git a/openspec/changes/implement-row-index/proposal.md b/openspec/changes/implement-row-index/proposal.md
new file mode 100644
index 0000000..f8cb00b
--- /dev/null
+++ b/openspec/changes/implement-row-index/proposal.md
@@ -0,0 +1,56 @@
+## Why
+
+The SQL on FHIR v2 specification defines a `%rowIndex` environment variable that
+holds the 0-based position of the current element within a collection being
+iterated by `forEach`, `forEachOrNull`, or `repeat`. It lets views capture
+element position for ordering or surrogate keys. The transpiler does not yet
+recognise it, so the nine in-scope tests in `sqlonfhir/tests/row_index.json`
+(pulled in by the submodule bump in #9) currently fail and show as red in the
+test report. Per the project constitution (Principle I), in-scope tests must
+pass.
+
+## What Changes
+
+- Recognise `%rowIndex` as a built-in FHIRPath environment variable during
+  column expression transpilation, instead of rejecting it as an undefined
+  constant.
+- Resolve `%rowIndex` to the 0-based index of the innermost active iteration:
+  - Inside `forEach` / `forEachOrNull`: the iterated element's position, using
+    the `OPENJSON` `[key]` column already captured by the walker.
+  - Inside `repeat`: the position within the flattened depth-first traversal of
+    the recursive result.
+  - With no active iteration (resource level, or a `unionAll` branch with no
+    iteration of its own): `0`.
+- Ensure correct behaviour across nesting and composition: nested `forEach`
+  levels each resolve to their own index, and `unionAll` branches resolve
+  independently based on whether the branch introduces its own iteration.
+- Cast the resolved value to T-SQL `INT` so it satisfies the `integer` column
+  type.
+
+## Capabilities
+
+### New Capabilities
+
+- `row-index-variable`: Resolution of the `%rowIndex` FHIRPath environment
+  variable to a 0-based T-SQL integer reflecting the current element's position
+  within the active `forEach`, `forEachOrNull`, or `repeat` iteration, or `0`
+  when no iteration is active.
+
+### Modified Capabilities
+
+<!-- None: no existing specs under openspec/specs/ define behaviour changed by this work. -->
+
+## Impact
+
+- `src/fhirpath/visitor.ts`: `visitExternalConstant` must resolve `%rowIndex`
+  from the transpiler context rather than throwing.
+- `src/fhirpath/transpiler.ts` and `TranspilerContext`: may need to expose the
+  active iteration's index expression to the visitor.
+- `src/queryGenerator/treeWalker/operators/forEach.ts`, `repeat.ts`,
+  `unionAll.ts`: thread the current iteration's index expression into the
+  transpiler context so `%rowIndex` resolves correctly across nesting and
+  composition.
+- `src/queryGenerator/treeWalker/cteTemplates.ts`: the `repeat` recursive CTE
+  must expose a stable depth-first traversal index for `%rowIndex` to reference.
+- Tests: the nine in-scope cases in `sqlonfhir/tests/row_index.json` move from
+  failing to passing; no production API surface changes.
diff --git a/openspec/changes/implement-row-index/specs/row-index-variable/spec.md b/openspec/changes/implement-row-index/specs/row-index-variable/spec.md
new file mode 100644
index 0000000..b94805e
--- /dev/null
+++ b/openspec/changes/implement-row-index/specs/row-index-variable/spec.md
@@ -0,0 +1,109 @@
+## ADDED Requirements
+
+### Requirement: Recognise %rowIndex as a built-in environment variable
+
+The transpiler SHALL recognise `%rowIndex` as a built-in FHIRPath environment
+variable in column `path` expressions. It MUST NOT reject `%rowIndex` as an
+undefined constant, regardless of whether the ViewDefinition declares any
+`constant` entries. The resolved value SHALL be emitted as valid T-SQL of type
+`INT` so that a column declared with `"type": "integer"` produces an integer
+result.
+
+#### Scenario: %rowIndex is accepted without a matching constant
+
+- **WHEN** a column `path` is `%rowIndex` and the ViewDefinition declares no
+  constant named `rowIndex`
+- **THEN** transpilation succeeds and the column expression resolves to a T-SQL
+  integer rather than raising an "is not defined" error
+
+#### Scenario: A user-defined constant does not shadow %rowIndex
+
+- **WHEN** `%rowIndex` appears in a column `path`
+- **THEN** it resolves to the iteration index defined by this capability and is
+  not interpreted as a user-supplied `constant` value
+
+### Requirement: Resolve %rowIndex to the innermost iteration index
+
+`%rowIndex` SHALL resolve to the 0-based position of the current element within
+the innermost active iteration introduced by `forEach` or `forEachOrNull`. When
+the same `select` chain nests multiple iterations, `%rowIndex` SHALL reflect the
+index of the nearest enclosing iteration, with each nesting level tracking its
+own independent index.
+
+#### Scenario: forEach exposes element position
+
+- **WHEN** a `forEach: "name"` select evaluates `%rowIndex` over a Patient whose
+  `name` collection has two entries
+- **THEN** the first iterated row reports `0` and the second reports `1`
+
+#### Scenario: forEachOrNull on a non-empty collection behaves like forEach
+
+- **WHEN** a `forEachOrNull: "name"` select evaluates `%rowIndex` over a
+  non-empty `name` collection
+- **THEN** the rows report their 0-based positions `0`, `1`, ...
+
+#### Scenario: forEachOrNull on an empty collection reports zero
+
+- **WHEN** a `forEachOrNull: "name"` select evaluates `%rowIndex` for a resource
+  whose `name` collection is empty, producing the single null-padded row
+- **THEN** `%rowIndex` for that row reports `0`
+
+#### Scenario: Nested forEach levels track independent indices
+
+- **WHEN** an outer `forEach: "contact"` containing an inner `forEach: "telecom"`
+  both evaluate `%rowIndex`
+- **THEN** the outer column reports the contact's index and the inner column
+  reports the telecom's index within that contact, each independent of the other
+
+### Requirement: Resolve %rowIndex to zero when no iteration is active
+
+`%rowIndex` SHALL resolve to `0` whenever it is evaluated outside any `forEach`,
+`forEachOrNull`, or `repeat` iteration, including at the resource (top) level.
+
+#### Scenario: Top-level %rowIndex is zero per resource
+
+- **WHEN** a column at the resource level (no `forEach`) evaluates `%rowIndex`
+- **THEN** every resource row reports `0`
+
+### Requirement: Resolve %rowIndex within repeat traversal
+
+When `%rowIndex` is evaluated inside a `repeat` select, it SHALL resolve to the
+0-based position of the current element within the flattened depth-first
+traversal produced by the recursive expansion, ordered so that each parent is
+immediately followed by its descendants.
+
+#### Scenario: repeat reports flattened traversal position
+
+- **WHEN** a `repeat: ["item"]` select over a QuestionnaireResponse whose items
+  form the depth-first sequence `1`, `1.1`, `1.2`, `2` evaluates `%rowIndex`
+- **THEN** those rows report `0`, `1`, `2`, `3` respectively
+
+### Requirement: Resolve %rowIndex independently within each unionAll branch
+
+Within a `unionAll`, each branch SHALL resolve `%rowIndex` according to its own
+iteration context. A branch that introduces its own `forEach` /
+`forEachOrNull` / `repeat` SHALL report that iteration's index, while a branch
+with no iteration of its own SHALL inherit `%rowIndex` from the enclosing
+context (which is `0` when no enclosing iteration exists).
+
+#### Scenario: Each iterating branch maintains its own sequence
+
+- **WHEN** a `unionAll` contains one branch with `forEach: "name"` and another
+  with `forEach: "contact"`, both evaluating `%rowIndex`
+- **THEN** the rows from each branch report 0-based indices over that branch's
+  own collection, independent of the other branch
+
+#### Scenario: A non-iterating branch inherits the enclosing index
+
+- **WHEN** a `unionAll` branch has no iteration expression of its own and
+  evaluates `%rowIndex`
+- **THEN** it reports the `%rowIndex` of the enclosing context - `0` at the top
+  level, or the enclosing `forEach` index when nested inside one
+
+#### Scenario: unionAll inside forEach mixes branch and inherited indices
+
+- **WHEN** a `unionAll` nested inside `forEach: "contact"` contains an iterating
+  branch (`forEach: "telecom"`) and a non-iterating branch, both evaluating
+  `%rowIndex`
+- **THEN** the iterating branch reports the telecom index while the
+  non-iterating branch reports the enclosing contact index
diff --git a/openspec/changes/implement-row-index/tasks.md b/openspec/changes/implement-row-index/tasks.md
new file mode 100644
index 0000000..52118ba
--- /dev/null
+++ b/openspec/changes/implement-row-index/tasks.md
@@ -0,0 +1,34 @@
+## 1. Establish the failing baseline (Red)
+
+- [ ] 1.1 Run the row_index suite with the database sourced (`set -a && source .env && set +a && SQLONFHIR_TEST_PATH=sqlonfhir/tests/row_index.json npm test`) and confirm all nine cases fail with the "Constant '%rowIndex' is not defined" error - establishing the red baseline before any change.
+- [ ] 1.2 Confirm the nine cases are not tagged `#experimental` and are therefore in scope for CI (`npm run test:ci`).
+
+## 2. Resolve %rowIndex in the visitor
+
+- [ ] 2.1 Add an optional `rowIndexExpr?: string` field to `TranspilerContext` in `src/fhirpath/visitor.ts` (and re-export point in `src/fhirpath/transpiler.ts`), documented as the SQL expression yielding the current iteration's 0-based index.
+- [ ] 2.2 In `visitExternalConstant`, special-case the name `rowIndex` before the constants lookup and the "not defined" error, returning `this.context.rowIndexExpr ?? "0"`.
+- [ ] 2.3 Verify the top-level scenario passes: `%rowIndex at top level` returns `0` for every resource row.
+- [ ] 2.4 Confirm no regression to the existing "Constant is not defined" behaviour for genuinely unknown `%` constants (the existing transpiler/visitor unit tests still pass).
+
+## 3. forEach and forEachOrNull index
+
+- [ ] 3.1 In `buildInnerCtx` (`src/queryGenerator/treeWalker/operators/forEach.ts`), set `rowIndexExpr` to `COALESCE(CAST(<alias>.[key] AS INT), 0)` so the iterated element's 0-based position is exposed, with the null-padded `OUTER APPLY` row mapping to `0`.
+- [ ] 3.2 Verify the `%rowIndex with forEach`, `%rowIndex with forEachOrNull`, `%rowIndex for surrogate key`, and `%rowIndex with nested forEach` cases pass, including independent indices per nesting level.
+
+## 4. repeat traversal index
+
+- [ ] 4.1 Extend the recursive CTE in `src/queryGenerator/treeWalker/cteTemplates.ts` to accumulate an ordering key `__order` alongside `__path`, zero-padding each segment's `[key]` to a fixed width (e.g. `RIGHT('0000000000' + CAST([key] AS NVARCHAR(10)), 10)`) so lexical ordering equals numeric depth-first pre-order.
+- [ ] 4.2 In `buildRepeatInnerCtx` (`src/queryGenerator/treeWalker/operators/repeat.ts`), set `rowIndexExpr` to `(ROW_NUMBER() OVER (PARTITION BY <ancestor partition keys> ORDER BY <cteAlias>.__order) - 1)`, partitioning on `ctx.partitionKeys` captured before the repeat key is appended.
+- [ ] 4.3 Verify the `%rowIndex with repeat` case returns `0, 1, 2, 3` for the depth-first item sequence, and inspect the generated SQL to confirm the window function references the joined CTE correctly.
+
+## 5. unionAll composition
+
+- [ ] 5.1 Confirm `walkUnionAll` requires no change: the three unionAll cases (`%rowIndex with unionAll`, `%rowIndex in unionAll without forEach`, `%rowIndex in unionAll inside forEach`) pass because branches inherit or override `rowIndexExpr` via the shared context.
+- [ ] 5.2 If any unionAll case fails, verify whether the inherited `forEach` alias remains in scope inside the correlated `CROSS APPLY (… UNION ALL …)` derived table, and adjust only if necessary.
+
+## 6. Quality gates and documentation
+
+- [ ] 6.1 Run the full suite with coverage and the database sourced (`set -a && source .env && set +a && npm run test:coverage`) and confirm all nine row_index cases pass with no regressions elsewhere.
+- [ ] 6.2 Run `npm run build`, `npm run lint`, and `npm run format:check` with zero errors, warnings, or formatting differences.
+- [ ] 6.3 Add or update narrative comments referencing the SQL on FHIR `%rowIndex` definition at the new resolution points, and add `John Grimes` as author on any file significantly changed.
+- [ ] 6.4 Review the diff for simplicity and remove any dead code before opening the PR (Fixes #11).

From 811227bd36ac64c8e9dfebf663cbc997d96cce6c Mon Sep 17 00:00:00 2001
From: John Grimes <John.Grimes@csiro.au>
Date: Fri, 29 May 2026 04:47:14 +1000
Subject: [PATCH 4/6] Update sqlonfhir submodule to upstream master

---
 sqlonfhir | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sqlonfhir b/sqlonfhir
index 27ee2c6..ee8625f 160000
--- a/sqlonfhir
+++ b/sqlonfhir
@@ -1 +1 @@
-Subproject commit 27ee2c65442a000b78beef4b4a2ab1517ba3efe4
+Subproject commit ee8625f8bca51a057c553d24dc4eed5844bbfb89

From d648d36acbf6e2853299c0e2164f1d5cc6a7bfc3 Mon Sep 17 00:00:00 2001
From: John Grimes <John.Grimes@csiro.au>
Date: Fri, 29 May 2026 04:59:36 +1000
Subject: [PATCH 5/6] Resolve %rowIndex environment variable in transpilation

Recognise the SQL on FHIR %rowIndex environment variable in column path
expressions and resolve it to the 0-based position of the current element
within the active iteration.

The visitor special-cases the reserved name before the user-constant
lookup, returning a per-iteration index expression supplied via a new
TranspilerContext.rowIndexExpr field, or 0 at the resource root. forEach
and forEachOrNull set it from the OPENJSON [key] column (with a COALESCE
so the null-padded forEachOrNull row reports 0). repeat sets it to a
ROW_NUMBER window ordered by a zero-padded __order accumulator added to
the recursive CTE, giving the depth-first pre-order position. unionAll
needs no change as branches inherit or override the expression through
the shared context.

This makes the nine in-scope row_index.json conformance tests pass.

Fixes #11
---
 openspec/changes/implement-row-index/tasks.md | 34 +++++++++----------
 src/fhirpath/visitor.ts                       | 17 ++++++++++
 src/queryGenerator/treeWalker/cteTemplates.ts | 16 +++++++++
 .../treeWalker/operators/forEach.ts           |  7 ++++
 .../treeWalker/operators/repeat.ts            | 14 ++++++++
 5 files changed, 71 insertions(+), 17 deletions(-)

diff --git a/openspec/changes/implement-row-index/tasks.md b/openspec/changes/implement-row-index/tasks.md
index 52118ba..de4b74b 100644
--- a/openspec/changes/implement-row-index/tasks.md
+++ b/openspec/changes/implement-row-index/tasks.md
@@ -1,34 +1,34 @@
 ## 1. Establish the failing baseline (Red)
 
-- [ ] 1.1 Run the row_index suite with the database sourced (`set -a && source .env && set +a && SQLONFHIR_TEST_PATH=sqlonfhir/tests/row_index.json npm test`) and confirm all nine cases fail with the "Constant '%rowIndex' is not defined" error - establishing the red baseline before any change.
-- [ ] 1.2 Confirm the nine cases are not tagged `#experimental` and are therefore in scope for CI (`npm run test:ci`).
+- [x] 1.1 Run the row_index suite with the database sourced (`set -a && source .env && set +a && SQLONFHIR_TEST_PATH=sqlonfhir/tests/row_index.json npm test`) and confirm all nine cases fail with the "Constant '%rowIndex' is not defined" error - establishing the red baseline before any change.
+- [x] 1.2 Confirm the nine cases are not tagged `#experimental` and are therefore in scope for CI (`npm run test:ci`).
 
 ## 2. Resolve %rowIndex in the visitor
 
-- [ ] 2.1 Add an optional `rowIndexExpr?: string` field to `TranspilerContext` in `src/fhirpath/visitor.ts` (and re-export point in `src/fhirpath/transpiler.ts`), documented as the SQL expression yielding the current iteration's 0-based index.
-- [ ] 2.2 In `visitExternalConstant`, special-case the name `rowIndex` before the constants lookup and the "not defined" error, returning `this.context.rowIndexExpr ?? "0"`.
-- [ ] 2.3 Verify the top-level scenario passes: `%rowIndex at top level` returns `0` for every resource row.
-- [ ] 2.4 Confirm no regression to the existing "Constant is not defined" behaviour for genuinely unknown `%` constants (the existing transpiler/visitor unit tests still pass).
+- [x] 2.1 Add an optional `rowIndexExpr?: string` field to `TranspilerContext` in `src/fhirpath/visitor.ts` (and re-export point in `src/fhirpath/transpiler.ts`), documented as the SQL expression yielding the current iteration's 0-based index.
+- [x] 2.2 In `visitExternalConstant`, special-case the name `rowIndex` before the constants lookup and the "not defined" error, returning `this.context.rowIndexExpr ?? "0"`.
+- [x] 2.3 Verify the top-level scenario passes: `%rowIndex at top level` returns `0` for every resource row.
+- [x] 2.4 Confirm no regression to the existing "Constant is not defined" behaviour for genuinely unknown `%` constants (the existing transpiler/visitor unit tests still pass).
 
 ## 3. forEach and forEachOrNull index
 
-- [ ] 3.1 In `buildInnerCtx` (`src/queryGenerator/treeWalker/operators/forEach.ts`), set `rowIndexExpr` to `COALESCE(CAST(<alias>.[key] AS INT), 0)` so the iterated element's 0-based position is exposed, with the null-padded `OUTER APPLY` row mapping to `0`.
-- [ ] 3.2 Verify the `%rowIndex with forEach`, `%rowIndex with forEachOrNull`, `%rowIndex for surrogate key`, and `%rowIndex with nested forEach` cases pass, including independent indices per nesting level.
+- [x] 3.1 In `buildInnerCtx` (`src/queryGenerator/treeWalker/operators/forEach.ts`), set `rowIndexExpr` to `COALESCE(CAST(<alias>.[key] AS INT), 0)` so the iterated element's 0-based position is exposed, with the null-padded `OUTER APPLY` row mapping to `0`.
+- [x] 3.2 Verify the `%rowIndex with forEach`, `%rowIndex with forEachOrNull`, `%rowIndex for surrogate key`, and `%rowIndex with nested forEach` cases pass, including independent indices per nesting level.
 
 ## 4. repeat traversal index
 
-- [ ] 4.1 Extend the recursive CTE in `src/queryGenerator/treeWalker/cteTemplates.ts` to accumulate an ordering key `__order` alongside `__path`, zero-padding each segment's `[key]` to a fixed width (e.g. `RIGHT('0000000000' + CAST([key] AS NVARCHAR(10)), 10)`) so lexical ordering equals numeric depth-first pre-order.
-- [ ] 4.2 In `buildRepeatInnerCtx` (`src/queryGenerator/treeWalker/operators/repeat.ts`), set `rowIndexExpr` to `(ROW_NUMBER() OVER (PARTITION BY <ancestor partition keys> ORDER BY <cteAlias>.__order) - 1)`, partitioning on `ctx.partitionKeys` captured before the repeat key is appended.
-- [ ] 4.3 Verify the `%rowIndex with repeat` case returns `0, 1, 2, 3` for the depth-first item sequence, and inspect the generated SQL to confirm the window function references the joined CTE correctly.
+- [x] 4.1 Extend the recursive CTE in `src/queryGenerator/treeWalker/cteTemplates.ts` to accumulate an ordering key `__order` alongside `__path`, zero-padding each segment's `[key]` to a fixed width (e.g. `RIGHT('0000000000' + CAST([key] AS NVARCHAR(10)), 10)`) so lexical ordering equals numeric depth-first pre-order.
+- [x] 4.2 In `buildRepeatInnerCtx` (`src/queryGenerator/treeWalker/operators/repeat.ts`), set `rowIndexExpr` to `(ROW_NUMBER() OVER (PARTITION BY <ancestor partition keys> ORDER BY <cteAlias>.__order) - 1)`, partitioning on `ctx.partitionKeys` captured before the repeat key is appended.
+- [x] 4.3 Verify the `%rowIndex with repeat` case returns `0, 1, 2, 3` for the depth-first item sequence, and inspect the generated SQL to confirm the window function references the joined CTE correctly.
 
 ## 5. unionAll composition
 
-- [ ] 5.1 Confirm `walkUnionAll` requires no change: the three unionAll cases (`%rowIndex with unionAll`, `%rowIndex in unionAll without forEach`, `%rowIndex in unionAll inside forEach`) pass because branches inherit or override `rowIndexExpr` via the shared context.
-- [ ] 5.2 If any unionAll case fails, verify whether the inherited `forEach` alias remains in scope inside the correlated `CROSS APPLY (… UNION ALL …)` derived table, and adjust only if necessary.
+- [x] 5.1 Confirm `walkUnionAll` requires no change: the three unionAll cases (`%rowIndex with unionAll`, `%rowIndex in unionAll without forEach`, `%rowIndex in unionAll inside forEach`) pass because branches inherit or override `rowIndexExpr` via the shared context.
+- [x] 5.2 If any unionAll case fails, verify whether the inherited `forEach` alias remains in scope inside the correlated `CROSS APPLY (… UNION ALL …)` derived table, and adjust only if necessary. (No change needed; all three unionAll cases pass.)
 
 ## 6. Quality gates and documentation
 
-- [ ] 6.1 Run the full suite with coverage and the database sourced (`set -a && source .env && set +a && npm run test:coverage`) and confirm all nine row_index cases pass with no regressions elsewhere.
-- [ ] 6.2 Run `npm run build`, `npm run lint`, and `npm run format:check` with zero errors, warnings, or formatting differences.
-- [ ] 6.3 Add or update narrative comments referencing the SQL on FHIR `%rowIndex` definition at the new resolution points, and add `John Grimes` as author on any file significantly changed.
-- [ ] 6.4 Review the diff for simplicity and remove any dead code before opening the PR (Fixes #11).
+- [x] 6.1 Run the full suite with coverage and the database sourced (`set -a && source .env && set +a && npm run test:coverage`) and confirm all nine row_index cases pass with no regressions elsewhere.
+- [x] 6.2 Run `npm run build`, `npm run lint`, and `npm run format:check` with zero errors, warnings, or formatting differences.
+- [x] 6.3 Add or update narrative comments referencing the SQL on FHIR `%rowIndex` definition at the new resolution points, and add `John Grimes` as author on any file significantly changed.
+- [x] 6.4 Review the diff for simplicity and remove any dead code before opening the PR (Fixes #11).
diff --git a/src/fhirpath/visitor.ts b/src/fhirpath/visitor.ts
index b6c14db..ea83df0 100644
--- a/src/fhirpath/visitor.ts
+++ b/src/fhirpath/visitor.ts
@@ -1,5 +1,7 @@
 /**
  * FHIRPath to T-SQL visitor implementation using ANTLR.
+ *
+ * @author John Grimes
  */
 
 import { AbstractParseTreeVisitor } from "antlr4ts/tree/AbstractParseTreeVisitor";
@@ -55,6 +57,11 @@ export interface TranspilerContext {
   currentForEachAlias?: string; // The OPENJSON table alias (e.g., "forEach_0")
   forEachSource?: string; // The JSON source being iterated (e.g., "r.json")
   forEachPath?: string; // The JSON path being iterated (e.g., "$.name")
+  // The SQL expression yielding the current iteration's 0-based index, used to
+  // resolve the SQL on FHIR `%rowIndex` environment variable. Each iteration
+  // operator (forEach, forEachOrNull, repeat) sets this to the expression that
+  // produces that iteration's position; absent at the resource root.
+  rowIndexExpr?: string;
   testId?: string; // Optional test identifier for parallel test execution
 }
 
@@ -452,6 +459,16 @@ export class FHIRPathToTSqlVisitor
       constantName = ctx.STRING()?.text.slice(1, -1) ?? "";
     }
 
+    // `%rowIndex` is a built-in SQL on FHIR environment variable holding the
+    // 0-based position of the current element within the active forEach,
+    // forEachOrNull, or repeat iteration. It is reserved, so it is resolved
+    // before the user-defined constants lookup and the "not defined" error, and
+    // a user constant named `rowIndex` cannot shadow it. With no active
+    // iteration (resource root) it resolves to 0.
+    if (constantName === "rowIndex") {
+      return this.context.rowIndexExpr ?? "0";
+    }
+
     // Check if the constant is defined in the context
     if (
       this.context.constants &&
diff --git a/src/queryGenerator/treeWalker/cteTemplates.ts b/src/queryGenerator/treeWalker/cteTemplates.ts
index 05f80f1..be462e4 100644
--- a/src/queryGenerator/treeWalker/cteTemplates.ts
+++ b/src/queryGenerator/treeWalker/cteTemplates.ts
@@ -9,6 +9,8 @@
  * If a JSON object key contains a literal `.`, two distinct nodes could
  * theoretically produce equal `__path` strings. FHIR JSON keys do not
  * contain dots in practice; not a blocker.
+ *
+ * @author John Grimes
  */
 
 import type { CteDefinition, PartitionKey } from "./types.js";
@@ -81,6 +83,7 @@ function buildAnchorMember(args: BuildRepeatCteArgs): string {
   return `  SELECT
     ${projLines},
     CAST(${chain.lastAlias}.[key] AS NVARCHAR(MAX)) AS __path,
+    CAST(${orderSegment(chain.lastAlias)} AS NVARCHAR(MAX)) AS __order,
     ${chain.lastAlias}.value AS item_json,
     0 AS depth
   ${fromClause}${ancestorApplies}
@@ -98,12 +101,25 @@ function buildRecursiveMember(
   return `  SELECT
     ${head},
     cte.__path + '.' + CAST(${chain.lastAlias}.[key] AS NVARCHAR(4000)) AS __path,
+    cte.__order + '.' + ${orderSegment(chain.lastAlias)} AS __order,
     ${chain.lastAlias}.value AS item_json,
     cte.depth + 1
   FROM ${cteAlias} AS cte
   ${chain.applyClauses}`;
 }
 
+/**
+ * Builds one segment of the `__order` accumulator: the element's `[key]`
+ * zero-padded to a fixed width so that lexical ordering of the `.`-joined
+ * order string is equivalent to numeric depth-first (pre-order) traversal.
+ * Without padding, lexical order would break once a level has ten or more
+ * elements (e.g. `"10" < "2"`). This is what `%rowIndex` orders by inside a
+ * `repeat`. A 10-character pad assumes no single level exceeds 10^10 elements.
+ */
+function orderSegment(alias: string): string {
+  return `RIGHT('0000000000' + CAST(${alias}.[key] AS NVARCHAR(10)), 10)`;
+}
+
 /**
  * Builds the CROSS APPLY OPENJSON chain for a (possibly multi-segment) path.
  * For "a.b.c" produces three chained APPLYs; the last alias is `finalAlias`.
diff --git a/src/queryGenerator/treeWalker/operators/forEach.ts b/src/queryGenerator/treeWalker/operators/forEach.ts
index 7d64425..21b98c7 100644
--- a/src/queryGenerator/treeWalker/operators/forEach.ts
+++ b/src/queryGenerator/treeWalker/operators/forEach.ts
@@ -8,6 +8,8 @@
  *
  * Path-handling parity is delegated to PathParser (`.where()`, `.first()`,
  * array indexing, multi-segment array flattening).
+ *
+ * @author John Grimes
  */
 
 import type { TranspilerContext } from "../../../fhirpath/transpiler.js";
@@ -97,6 +99,11 @@ function buildInnerCtx(
     currentForEachAlias: alias,
     forEachSource: ctx.source,
     forEachPath: `$.${rawPath}`,
+    // `%rowIndex` resolves to the iterated element's 0-based position, which is
+    // the OPENJSON `[key]` column. For forEachOrNull over an empty collection
+    // the OUTER APPLY yields a single null-padded row whose `[key]` is NULL;
+    // the spec requires `%rowIndex` to be 0 for that row, hence the COALESCE.
+    rowIndexExpr: `COALESCE(CAST(${alias}.[key] AS INT), 0)`,
   };
   const innerKey: PartitionKey = {
     name: `${alias}_key`,
diff --git a/src/queryGenerator/treeWalker/operators/repeat.ts b/src/queryGenerator/treeWalker/operators/repeat.ts
index e67c72c..15fc091 100644
--- a/src/queryGenerator/treeWalker/operators/repeat.ts
+++ b/src/queryGenerator/treeWalker/operators/repeat.ts
@@ -5,6 +5,8 @@
  * plus a content-derived `__path` for stable identity across re-evaluations.
  * The Fragment's `fromExtensions` is an INNER JOIN to the CTE on the partition key
  * `[id]`; sibling-level composite-key joins are added by `mergeSiblings`.
+ *
+ * @author John Grimes
  */
 
 import type { TranspilerContext } from "../../../fhirpath/transpiler.js";
@@ -116,12 +118,24 @@ function buildRepeatInnerCtx(
     sqlExpr: `${cteAlias}.__path`,
     sqlType: SQL_NVARCHAR_MAX,
   };
+  // `%rowIndex` inside a repeat is the 0-based position within the flattened
+  // depth-first traversal. The CTE exposes a padded `__order` accumulator whose
+  // lexical order matches pre-order; ROW_NUMBER over it (less one) yields the
+  // index. Partitioning on the ancestor keys captured before the repeat key is
+  // appended (the resource, and any enclosing forEach element) restarts the
+  // sequence per partition. The window lives in the outer SELECT, which already
+  // INNER JOINs the CTE, so the reference is in scope.
+  const partitionCols = ctx.partitionKeys
+    .map((k) => `${cteAlias}.[${k.name}]`)
+    .join(", ");
+  const partitionClause = partitionCols ? `PARTITION BY ${partitionCols} ` : "";
   const innerTranspilerCtx: TranspilerContext = {
     ...ctx.transpilerCtx,
     iterationContext: `${cteAlias}.item_json`,
     currentForEachAlias: cteAlias,
     forEachSource: ctx.source,
     forEachPath: paths.map((p) => `$.${p}`).join(", "),
+    rowIndexExpr: `(ROW_NUMBER() OVER (${partitionClause}ORDER BY ${cteAlias}.__order) - 1)`,
   };
   // Propagate the join into ancestorApplies so any *nested* Repeat builds
   // its CTE anchor with this CTE in scope.

From e01fba58319f97d9003725a6a5faf0bad743f7d7 Mon Sep 17 00:00:00 2001
From: John Grimes <John.Grimes@csiro.au>
Date: Fri, 29 May 2026 05:03:45 +1000
Subject: [PATCH 6/6] Archive implement-row-index change and sync
 row-index-variable spec

Sync the row-index-variable capability into the main specs and move the
completed change to the archive.
---
 .../.openspec.yaml                            |   0
 .../2026-05-29-implement-row-index}/design.md |   0
 .../proposal.md                               |   0
 .../specs/row-index-variable/spec.md          |   0
 .../2026-05-29-implement-row-index}/tasks.md  |   0
 openspec/specs/row-index-variable/spec.md     | 118 ++++++++++++++++++
 6 files changed, 118 insertions(+)
 rename openspec/changes/{implement-row-index => archive/2026-05-29-implement-row-index}/.openspec.yaml (100%)
 rename openspec/changes/{implement-row-index => archive/2026-05-29-implement-row-index}/design.md (100%)
 rename openspec/changes/{implement-row-index => archive/2026-05-29-implement-row-index}/proposal.md (100%)
 rename openspec/changes/{implement-row-index => archive/2026-05-29-implement-row-index}/specs/row-index-variable/spec.md (100%)
 rename openspec/changes/{implement-row-index => archive/2026-05-29-implement-row-index}/tasks.md (100%)
 create mode 100644 openspec/specs/row-index-variable/spec.md

diff --git a/openspec/changes/implement-row-index/.openspec.yaml b/openspec/changes/archive/2026-05-29-implement-row-index/.openspec.yaml
similarity index 100%
rename from openspec/changes/implement-row-index/.openspec.yaml
rename to openspec/changes/archive/2026-05-29-implement-row-index/.openspec.yaml
diff --git a/openspec/changes/implement-row-index/design.md b/openspec/changes/archive/2026-05-29-implement-row-index/design.md
similarity index 100%
rename from openspec/changes/implement-row-index/design.md
rename to openspec/changes/archive/2026-05-29-implement-row-index/design.md
diff --git a/openspec/changes/implement-row-index/proposal.md b/openspec/changes/archive/2026-05-29-implement-row-index/proposal.md
similarity index 100%
rename from openspec/changes/implement-row-index/proposal.md
rename to openspec/changes/archive/2026-05-29-implement-row-index/proposal.md
diff --git a/openspec/changes/implement-row-index/specs/row-index-variable/spec.md b/openspec/changes/archive/2026-05-29-implement-row-index/specs/row-index-variable/spec.md
similarity index 100%
rename from openspec/changes/implement-row-index/specs/row-index-variable/spec.md
rename to openspec/changes/archive/2026-05-29-implement-row-index/specs/row-index-variable/spec.md
diff --git a/openspec/changes/implement-row-index/tasks.md b/openspec/changes/archive/2026-05-29-implement-row-index/tasks.md
similarity index 100%
rename from openspec/changes/implement-row-index/tasks.md
rename to openspec/changes/archive/2026-05-29-implement-row-index/tasks.md
diff --git a/openspec/specs/row-index-variable/spec.md b/openspec/specs/row-index-variable/spec.md
new file mode 100644
index 0000000..0cb3b66
--- /dev/null
+++ b/openspec/specs/row-index-variable/spec.md
@@ -0,0 +1,118 @@
+# row-index-variable
+
+## Purpose
+
+Define how the transpiler recognises and resolves the `%rowIndex` built-in
+FHIRPath environment variable, so that column `path` expressions can reference
+the 0-based position of the current element within the active iteration context
+and emit a valid T-SQL integer.
+
+## Requirements
+
+### Requirement: Recognise %rowIndex as a built-in environment variable
+
+The transpiler SHALL recognise `%rowIndex` as a built-in FHIRPath environment
+variable in column `path` expressions. It MUST NOT reject `%rowIndex` as an
+undefined constant, regardless of whether the ViewDefinition declares any
+`constant` entries. The resolved value SHALL be emitted as valid T-SQL of type
+`INT` so that a column declared with `"type": "integer"` produces an integer
+result.
+
+#### Scenario: %rowIndex is accepted without a matching constant
+
+- **WHEN** a column `path` is `%rowIndex` and the ViewDefinition declares no
+  constant named `rowIndex`
+- **THEN** transpilation succeeds and the column expression resolves to a T-SQL
+  integer rather than raising an "is not defined" error
+
+#### Scenario: A user-defined constant does not shadow %rowIndex
+
+- **WHEN** `%rowIndex` appears in a column `path`
+- **THEN** it resolves to the iteration index defined by this capability and is
+  not interpreted as a user-supplied `constant` value
+
+### Requirement: Resolve %rowIndex to the innermost iteration index
+
+`%rowIndex` SHALL resolve to the 0-based position of the current element within
+the innermost active iteration introduced by `forEach` or `forEachOrNull`. When
+the same `select` chain nests multiple iterations, `%rowIndex` SHALL reflect the
+index of the nearest enclosing iteration, with each nesting level tracking its
+own independent index.
+
+#### Scenario: forEach exposes element position
+
+- **WHEN** a `forEach: "name"` select evaluates `%rowIndex` over a Patient whose
+  `name` collection has two entries
+- **THEN** the first iterated row reports `0` and the second reports `1`
+
+#### Scenario: forEachOrNull on a non-empty collection behaves like forEach
+
+- **WHEN** a `forEachOrNull: "name"` select evaluates `%rowIndex` over a
+  non-empty `name` collection
+- **THEN** the rows report their 0-based positions `0`, `1`, ...
+
+#### Scenario: forEachOrNull on an empty collection reports zero
+
+- **WHEN** a `forEachOrNull: "name"` select evaluates `%rowIndex` for a resource
+  whose `name` collection is empty, producing the single null-padded row
+- **THEN** `%rowIndex` for that row reports `0`
+
+#### Scenario: Nested forEach levels track independent indices
+
+- **WHEN** an outer `forEach: "contact"` containing an inner `forEach: "telecom"`
+  both evaluate `%rowIndex`
+- **THEN** the outer column reports the contact's index and the inner column
+  reports the telecom's index within that contact, each independent of the other
+
+### Requirement: Resolve %rowIndex to zero when no iteration is active
+
+`%rowIndex` SHALL resolve to `0` whenever it is evaluated outside any `forEach`,
+`forEachOrNull`, or `repeat` iteration, including at the resource (top) level.
+
+#### Scenario: Top-level %rowIndex is zero per resource
+
+- **WHEN** a column at the resource level (no `forEach`) evaluates `%rowIndex`
+- **THEN** every resource row reports `0`
+
+### Requirement: Resolve %rowIndex within repeat traversal
+
+When `%rowIndex` is evaluated inside a `repeat` select, it SHALL resolve to the
+0-based position of the current element within the flattened depth-first
+traversal produced by the recursive expansion, ordered so that each parent is
+immediately followed by its descendants.
+
+#### Scenario: repeat reports flattened traversal position
+
+- **WHEN** a `repeat: ["item"]` select over a QuestionnaireResponse whose items
+  form the depth-first sequence `1`, `1.1`, `1.2`, `2` evaluates `%rowIndex`
+- **THEN** those rows report `0`, `1`, `2`, `3` respectively
+
+### Requirement: Resolve %rowIndex independently within each unionAll branch
+
+Within a `unionAll`, each branch SHALL resolve `%rowIndex` according to its own
+iteration context. A branch that introduces its own `forEach` /
+`forEachOrNull` / `repeat` SHALL report that iteration's index, while a branch
+with no iteration of its own SHALL inherit `%rowIndex` from the enclosing
+context (which is `0` when no enclosing iteration exists).
+
+#### Scenario: Each iterating branch maintains its own sequence
+
+- **WHEN** a `unionAll` contains one branch with `forEach: "name"` and another
+  with `forEach: "contact"`, both evaluating `%rowIndex`
+- **THEN** the rows from each branch report 0-based indices over that branch's
+  own collection, independent of the other branch
+
+#### Scenario: A non-iterating branch inherits the enclosing index
+
+- **WHEN** a `unionAll` branch has no iteration expression of its own and
+  evaluates `%rowIndex`
+- **THEN** it reports the `%rowIndex` of the enclosing context - `0` at the top
+  level, or the enclosing `forEach` index when nested inside one
+
+#### Scenario: unionAll inside forEach mixes branch and inherited indices
+
+- **WHEN** a `unionAll` nested inside `forEach: "contact"` contains an iterating
+  branch (`forEach: "telecom"`) and a non-iterating branch, both evaluating
+  `%rowIndex`
+- **THEN** the iterating branch reports the telecom index while the
+  non-iterating branch reports the enclosing contact index