メニュー
Deep code review after beads have landed — random exploration + cross-agent review, alternating. Use every 30–60 min during active implementation, or after any epic lands.
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
| name | deep-review |
| description | Deep code review after beads have landed — random exploration + cross-agent review, alternating. Use every 30–60 min during active implementation, or after any epic lands. |
Self-review (inline, after each bead) catches most bugs in the code an agent just wrote. Deep review catches the boundary bugs: code one agent wrote being called wrong by another agent, integration mismatches, and latent bugs in code no-one's been staring at.
Use the verbatim prompts at .flywheel/prompts/deep-review.md,
alternating Round A and Round B.
Back to bead space. Create fix-beads for the bug classes that keep appearing. The real problem isn't the individual bug, it's the pattern.
Deep review — random exploration + cross-agent review, alternating. Finds integration bugs that self-review misses. Run every 30–60 min during active implementation.
Overview of Forge's Agentic Coding Flywheel methodology. Use to route between plan, bead, and code space. See FLYWHEEL.md at the repo root.
End-of-session ritual. Close finished beads, file new ones for remaining work, run verify, commit in logical groupings, push. Work is not complete until git push succeeds.
Start a new Flywheel planning round. Produce initial markdown plan, route to competing frontier models, synthesize hybrid, refine 4–5×. Use before any coding begins on a new feature.
Translate a polished markdown plan into self-contained beads in .beads/beads.jsonl. Every bead must be executable without reopening the plan. Use after the plan has converged.
Polishing pass over all open beads. Run 4–6 times. "Check your beads N times, implement once." Use after plan-to-beads and between refinement rounds.
