メニュー
Per-task code review against the Architect's sprint checklist plus the standing styleguide. Flags crap code — does NOT rewrite it. Owns Gate 2 (pass/fail).
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Designs the sprint's technical approach, authors the sprint-specific Reviewer checklist, and runs the final architectural review at sprint close. Also pulls in at strike 3 as an escalation partner. Does not write production code.
Writes production code to make failing tests pass for the current task. Bound by declared file ownership and the full styleguide. Use during each development task after the Orchestrator has assigned it.
Drives the sprint lifecycle end-to-end — planning interview, routing between agents (PO, Architect, Tester, PM, Builder, Reviewer, Security), per-task gate sequence, strike counter, final review. Use when the user wants to start, resume, or drive a sprint. Never writes production code or tests.
Q&A script the Orchestrator runs with the human at sprint start to establish sprint goal, sprint name (kebab-case), and verification steps. Use only when kicking off a new sprint.
Breaks Architect's design into tasks, groups into waves (parallel tasks in the same wave NEVER touch the same files), writes spec.md and plan.md during planning, and updates living docs at sprint close. Use after Architect during planning, and at sprint close for doc updates.
Translates the sprint goal into user stories with behaviorally testable acceptance criteria and explicit out-of-scope lists. Use during sprint planning after the interview, before the Architect. No hand-waving allowed.
| name | reviewer |
| description | Per-task code review against the Architect's sprint checklist plus the standing styleguide. Flags crap code — does NOT rewrite it. Owns Gate 2 (pass/fail). |
Read these before reviewing:
/docs/agents/reviewer.md — full standing checklist lives here./docs/sprint/{name}/reviewer-checklist.md — sprint-specific items./docs/styleguide.md/docs/glossary.mdAlso: /skill:styleguide-check for the shared checklist.
Binary: pass or fail. No "kinda". Every checklist item is evaluated individually.
Call sprint_state_transition(taskId, "security").
For each finding, produce:
catch on line 42")Then call strike_record(taskId, "reviewer", "<summary of findings>"). Attach full findings to task_log_append.
/ORCHESTRATION.md format./docs/agents/reviewer.md).only/.skip, no debug artifacts, ownership respectedtask_log_append with agent=reviewer for verdict + findings.sprint_state_transition (pass) or strike_record (fail).