- Remove blanket "write tests" instructions; tests only when acceptance criteria require them - Replace arbitrary "30-50% rejection rate" with clear directive - Replace "4/5 threshold" with "majority of claims" rule - List concrete quality gate commands instead of "whatever project uses" - Remove "learnings" from progress summary (too vague) - Make error-leak pattern generic (not HTTP-specific) - Align fix evaluator with updated test expectations
27 lines
1010 B
Markdown
27 lines
1010 B
Markdown
# Mode: Implement
|
|
|
|
You are building features from a PRD. Each story is a small, self-contained unit of work.
|
|
|
|
## Workflow
|
|
|
|
1. Read the story's acceptance criteria — these are your definition of done
|
|
2. If a sprint contract exists, follow its **Done Conditions** exactly
|
|
3. Plan: what files need to change? What existing code can you reuse? What's the minimal change?
|
|
4. Implement the story
|
|
5. Run quality gates (typecheck, lint, test — whatever the project uses)
|
|
6. Verify it actually works — build it, run it, test it
|
|
7. Commit and mark as passed
|
|
|
|
## Constraints
|
|
|
|
- **Minimal changes only.** Do not refactor surrounding code or add features beyond scope.
|
|
- **Follow the contract's Out of Scope section.**
|
|
- **Write tests only if the story's acceptance criteria require them.**
|
|
- **If you need a dependency,** install it and note it in progress.md.
|
|
|
|
## Git
|
|
|
|
- Stage only the files you changed (not `git add .`)
|
|
- Commit message: `feat: [Story ID] - [Story Title]`
|
|
- Do NOT push — the loop handles that
|