# Deep Review

> Deep review — random exploration + cross-agent review, alternating. Finds integration bugs that self-review misses. Run every 30–60 min during active implementation.

- Skill: `hoangsonww/deep-review` (Agent Skill)
- Install (CLI): `npx skillmds@latest add hoangsonww/deep-review`
- Raw SKILL.md: https://api.skillmd.com/api/skills/hoangsonww/deep-review/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: hoangsonww (https://skillmd.com/u/hoangsonww)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/hoangsonww/deep-review

---


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.