// Deep review — random exploration + cross-agent review, alternating. Finds integration bugs that self-review misses. Run every 30–60 min during active implementation.
| name | deep-review |
| description | Deep review — random exploration + cross-agent review, alternating. Finds integration bugs that self-review misses. Run every 30–60 min during active implementation. |
Use the verbatim prompts at .flywheel/prompts/deep-review.md,
alternating Round A (random exploration) and Round B (cross-agent
review).
Run this on 1–2 agents who just finished a bead, not the whole swarm. Continue until two consecutive rounds from different agents come back clean.
If agents keep finding bugs after 4+ rounds, the real issue is a pattern — go back to bead space and create fix-beads for the bug class.
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.
Break the spell of local productivity. Ask whether completing all open beads actually closes the gap to the project goal. Use at milestones or when busy agents feel directionally off.
