← ClaudeAtlas

rcode-dev-storylisted

Execute an approved story file by writing tests and code that fulfill every acceptance criterion. Activates when the user says "dev this story", "implement story {id}", "execute the story", "code the next story", "run dev-story on", or "implement .rcode/phases/{phase}/stories/{file}". Do NOT use without a prepared story file (use rcode-create-story first).
hanzlahabib/rcode · ★ 0 · AI & Automation · score 72
Install: claude install-skill hanzlahabib/rcode
@.rcode/references/karpathy-guidelines.md ## Overview Execute an approved story file by writing tests and code that fulfill every acceptance criterion. ## Workflow Follow the instructions in ./workflow.md. ## Output Format - Reads story file first; executes tasks in order - Marks tasks [x] only when implementation AND tests pass - Updates story's File List and Dev Agent Record sections - Runs two-stage automated review before marking complete: spec compliance → code quality - Reports: "Story complete. N tasks done. Tests: PASS (X). Files: [list]. Reviews: SPEC ✅ QUALITY ✅" - Do NOT invent scope beyond the story - Do NOT commit with red tests ## Review Protocol After all tasks complete, dispatches two fresh reviewer subagents before handing off to human review: **Stage 1 — Spec Compliance:** Confirms every AC is implemented, nothing extra was built. Repeats until COMPLIANT. **Stage 2 — Code Quality:** Reviews naming, error handling, test depth, security, maintainability. Fixes High-severity issues; logs Medium issues for human reviewer. Repeats until APPROVED/APPROVED_WITH_NOTES. ## Model Selection When dispatching reviewer subagents or sub-tasks: - Mechanical tasks (isolated, clear spec, 1-2 files) → cheapest/fastest model - Integration tasks (multi-file, pattern matching) → standard model - Architecture, design, or review tasks → most capable model ## Implementer Status Protocol When running as a subagent implementer, report one of: - **DONE** — all requirem