Skip to content
cccskills
FreePublished on GitHub

deep-review

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.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md1.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

/deep-review — random-exploration × cross-agent

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.

Prompts

Use the verbatim prompts at .flywheel/prompts/deep-review.md, alternating Round A and Round B.

How to run

  • Pick 1–2 agents who just finished a bead. Don't stop the whole swarm.
  • Send Round A to one, Round B to another.
  • After they report, swap: send Round A to the second agent, Round B to the first.
  • Continue until two consecutive rounds come back clean from different agents.

What the two rounds find

  • Round A (random exploration): latent bugs in utility modules, error paths, and edge branches that nobody has reviewed because nobody's been touching them.
  • Round B (cross-agent): boundary mismatches between agents' code, root causes behind symptoms, "I trusted the other agent's assumption and they weren't thinking about X."

If agents keep finding bugs after 4+ rounds

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.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Scaffold a new Forge subagent (planner/architect/executor/reviewer/debugger/memory-style). Use when adding anything to src/agents/.

The English summary is being prepared. Showing the original description.

hoangsonww/Forge-Agentic-Coding-CLI26Updated Sep 28, 2026

Scaffold a new Forge subagent (planner/architect/executor/reviewer/debugger/memory-style).

The English summary is being prepared. Showing the original description.

hoangsonww/Forge-Agentic-Coding-CLI26Updated Sep 28, 2026

Scaffold a new model provider for Forge — class implementation, registry wiring, providerEnum entry, local-catalog classification, and unit test with mocked transport. Use for anything under src/models/.

The English summary is being prepared. Showing the original description.

hoangsonww/Forge-Agentic-Coding-CLI26Updated Sep 28, 2026

Scaffold a new model provider for Forge — class, registry wiring, providerEnum entry, local-catalog classification, router check, and a unit test with mocked transport.

The English summary is being prepared. Showing the original description.

hoangsonww/Forge-Agentic-Coding-CLI26Updated Sep 28, 2026

Scaffold a new Forge tool end-to-end — type, implementation, registration, permission/risk classification, and unit test. Use when adding anything to src/tools/.

The English summary is being prepared. Showing the original description.

hoangsonww/Forge-Agentic-Coding-CLI26Updated Sep 28, 2026

Scaffold a new Forge tool — implementation, registration, permission/risk metadata, sandbox routing, and a unit test. Use when adding anything to src/tools/.

The English summary is being prepared. Showing the original description.

hoangsonww/Forge-Agentic-Coding-CLI26Updated Sep 28, 2026

See all skills by hoangsonww

Report a problem with this skill