Simplify the evels that were needed and make them pass on OpenCode

[justinmclean]

Summary

Run all 1000+ evals on OpenCode and Claude - all pass on Claude, after these changes only 3 fail on OpenCode.

Type of change

• Skill change (.claude/skills/<name>/) — eval fixtures updated below
• Tool / bridge contract (tools/<system>/*.md)
• Python package (tools/*/ with pyproject.toml)
• Groovy reference impl
• Cross-cutting (RFC, AGENTS.md, sandbox, privacy-LLM)
• Documentation (docs/, README.md, CONTRIBUTING.md)
• Project template (projects/_template/)
• CI / dev loop (prek, workflows, validators)
• Other: evals

Test plan

• prek run --all-files passes
• For Python packages touched: uv run pytest / ruff check / mypy passes
• For Groovy bridges touched: command-line invocation tested end-to-end
• For skill changes: eval suite passes for the affected skill
  (PYTHONPATH=tools/skill-evals/src python3 -m skill_evals.runner tools/skill-evals/evals/<skill>/)
• For skill behaviour changes: a new or updated eval fixture is included in this PR
  (a regression test for the bug fixed / the behaviour added — see CONTRIBUTING.md)
• Other:

[potiuk]

Coool!

[justinmclean]

Note that, as the tests are not 100% deterministic, we may need a few more tweaks, but it's in a good place, I feel.

[potiuk]

Note that, as the tests are not 100% deterministic, we may need a few more tweaks, but it's in a good place, I feel.

Yeah. We might want to improve it and automate further.