codex-review
Skill9 starsChanged 8 months agoMITView on GitHub
Code review via OpenAI Codex — review uncommitted changes, branches, or commits
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
ryanportfolioSkillapply-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 repository11 other files it gives its agents.
- add-buddySkill
- brainstormSkill
- campfireSkill
- codexSkill
- forgeSkill
- gemini-reviewSkill
- geminiSkill
- leaderboardSkill
- opencode-reviewSkill
- opencodeSkill
- tribunalSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 79 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Run the wrapper script via Bash.
- Very specific: line 27
No arguments → review uncommitted changes (--review-target uncommitted)
- Distinctive: line 30
Determine working directory: Must be inside a git repository.
- Distinctive: line 35
Add your own perspective: if you see issues Codex missed, or agree with specific points.
- Distinctive: line 65
Always verify we're in a git repo: before running. If not, tell the user.
“Common” is measured: kept by at least 6 in 10 of the 79 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/codex-review — Code Review via Codex
Get a code review from OpenAI's Codex CLI. Reviews uncommitted changes by default, or specify a branch or commit.
How to invoke
Run the wrapper script via Bash. IMPORTANT: Codex regularly takes 3-6 minutes for non-trivial tasks. You MUST set the Bash tool's timeout parameter to 420000 (7 minutes) to prevent Claude Code from killing the process before Codex finishes.
bash "${CLAUDE_PLUGIN_ROOT}/scripts/codex-run.sh" \
--prompt "Additional review instructions (optional)" \
--cwd "/path/to/repo" \
--mode review \
--review-target "uncommitted"Then read the output file and present the review to the user.
Step-by-step workflow
- Determine what to review:
- No arguments → review uncommitted changes (
--review-target uncommitted) - User specifies a branch →
--review-target branch:branch-name - User specifies a commit →
--review-target commit:SHA
- No arguments → review uncommitted changes (
- Determine working directory. Must be inside a git repository.
- Build the prompt. The wrapper automatically fetches the diff and builds a review prompt. If the user provides extra instructions (e.g., "focus on security"), pass them as
--prompt. - Run codex-run.sh with
--mode reviewvia the Bash tool. - Read the output file using the Read tool.
- Present the review to the user. Frame it as "Codex's code review:" with clear sections.
- Add your own perspective if you see issues Codex missed, or agree with specific points.
Review targets
| Target | Flag | Example |
| Uncommitted changes | --review-target uncommitted | /codex-review |
| Branch diff | --review-target branch:NAME | /codex-review branch:feature/auth |
| Specific commit | --review-target commit:SHA | /codex-review commit:abc1234 |
Options
| Flag | Default | Description |
--prompt | "" | Additional instructions for the review |
--cwd | current dir | Path to the git repository |
--mode | — | Must be review for this skill |
--review-target | uncommitted | What to review |
--timeout | from config (360s) | Max seconds to wait |
--model | from config | Override the Codex model |
Example invocations
/codex-review— review all uncommitted changes/codex-review branch:main— review diff from main to HEAD/codex-review commit:a1b2c3d— review a specific commit/codex-review "focus on security and SQL injection"— review with extra instructions
Rules
- Always verify we're in a git repo before running. If not, tell the user.
- If no changes exist, tell the user there's nothing to review instead of sending an empty diff.
- Present both perspectives — show Codex's review, then add your own observations.
- Don't auto-apply suggestions — present findings and let the user decide what to fix.
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.

