codex-review
Skill0 starsChanged 3 months agoMITView on GitHub
Codex review lifecycle - build the review bundle, generate the prompt, parse APPROVED/CHANGES_REQUIRED results, run the review-fix loop, and invalidate approval via the implementation fingerprint.
91 other projects use a version of this.
Adopted by
Most recently taken up by
- p-chan/agent-skillstheir own version, first seen Nov 8, 2026
- p-chan/skillstheir own version, first seen Nov 8, 2026
- Smirnov-Labs/claude-skillstheir own version, first seen Nov 8, 2026
- juriwiens/skillstheir own version, first seen Nov 8, 2026
- ryanportfolio/winuse-mcptheir own version, first seen Nov 8, 2026
- fab-codes/agent-workflow-templatetheir own version, first seen Nov 8, 2026
Used with
Projects with it also use addskill, apply-firmware and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ryanportfolioSkilladdskill
Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.
Also in 6 projects that use this
- ryanportfolioSkill
apply-firmware
Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.
Also in 6 projects that use this
- +10 more from ryanportfolio
Other versions91 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 91
- ClickHouse/ClickHouse★ 51ksame name
- chaseai-yt/claudex-loop★ 3.2ksame name
- morethanwords/tweb★ 2.7ksame name
- alinaqi/maggy★ 711same name
- alinaqi/claude-bootstrap★ 708same name
- ThibautBaissac/rails_ai_agents★ 665same name
- ai-analyst-lab/ai-analyst★ 304same name
- Sateezg/codex-bridge★ 248same name
- sd0xdev/sd0x-dev-flow★ 192same name
- sd0xdev/sd0x-harness★ 192same name
81 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- deploymentSkill
- feature-changelogSkill
- frappe-taskSkill
- git-finalizationSkill
- project-contextSkill
- task-implementationSkill
- task-planningSkill
- testing-taskSkill
The file
Files
Codex Review Skill
Manages the external Codex review of a completed implementation. Codex reviews only — it never modifies files; the bundle says so explicitly.
When to Use
reviewaction (stageimplementation/review_fixes, completion gate passed) → bundle + prompt (references/review-prompt-generation.md).apply-reviewaction (stagecodex_review) → parse result (references/review-result-parsing.md).- Stage
review_fixes→ fix loop (references/review-fix-loop.md). - Any post-approval change → (references/approval-invalidation.md).
Inputs
- Passing completion gate;
docs/ai-context/TASK_PLAN.md; the implementation summary atdocs/ai-context/implementation-summary.md; Git state; forapply-review, the raw Codex result text or file.
Outputs
docs/ai-context/reviews/round-NNN-prompt.md(viabin/frappe-workflow review bundle, which secret-scans and embeds the fingerprint).docs/ai-context/reviews/round-NNN-result.md— the original result, preserved verbatim.- State updates: round, prompt/result paths, fingerprint, status (pending → changes_required → … → approved), approved_at.
Preconditions
- Bundle:
validate completion-gatepasses. - Result parsing: a prompt for the current round exists and state is
codex_review. - Approval acceptance: current fingerprint == recorded fingerprint.
Stopping Conditions
APPROVEDaccepted → finalization (feature-changelog + project-context updates, review record) →validate finalization-gate→ready_for_commit. Done.CHANGES_REQUIRED→review_fixes; loop continues until approved.- Malformed result → reject with the format requirements; stay in
codex_review; never guess a status.
Prohibited
- Generating a prompt without a passing completion gate.
- Accepting any status other than exactly
APPROVED/CHANGES_REQUIRED. - Inventing, dropping, or "interpreting away" findings; the original result file is never edited.
- Accepting approval whose fingerprint mismatches the working tree.
- Applying a finding without validating it against the repository first.
Shared Rules
shared-workflow-rules.md, security-rules.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.