guide
Skill3 starsChanged 6 months agoApache-2.0View on GitHub
Codex guide for review-loop - the paired-session entry, review-pr and the shared .review-loop/config.md. Use when the user asks how review-loop works, what it can do, how to configure it, or for help with review-loop ('how do I use review-loop', 'review-loop help', 'what does the entry key do'). Not for starting a run or reviewing local changes (use review-loop) or a PR, branch or ref review (use review-pr).
20 other projects use a version of this.
Adopted by
Most recently taken up by
- cafe3310/public-agent-skillstheir own version, first seen Nov 8, 2026
- juanbermudez/skillstheir own version, first seen Nov 8, 2026
- Jasenpan1987/multi-codetheir own version, first seen Nov 8, 2026
- assisjp/specflowtheir own version, first seen Nov 1, 2026
- helderberto/agent-skillstheir own version, first seen Oct 13, 2026
- sangchane/claude-skillstheir own version, first seen Oct 13, 2026
Used with
Projects with it also use grill, brainstorm and 6 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.
renatorozasSkillgrill
Adversarial code review. Don't let me ship until the changes pass your scrutiny.
Also in 3 projects that use this
nicolasestremSkillbrainstorm
Structured idea generation and solution exploration with systematic analysis.
Also in 3 projects that use this
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 3 projects that use this
SentrySkillreview
Fixture review skill.
Also in 4 projects that use this
Hugging FaceSkillimplement
Make tests pass. Invoke after /write-tests produces failing tests.
Also in 3 projects that use this
NVIDIASkillresearch
Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.
Also in 3 projects that use this
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 20
- recharts/recharts★ 28ksame name
- cafe3310/public-agent-skills★ 256same name
- Senuto/nodeshub-seo-skills★ 40same name
- aleksander-dytko/ai-pm-workspace★ 34same name
- helderberto/agent-skills★ 19same name
- assisjp/specflow★ 17same name
- froster02/mini-Brain_skills★ 4same name
- MEKO747/claude-code-skill★ 4same name
- leepokai/claude-code-guide★ 2same name
- spleenteo/maestro★ 2same name
10 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 repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- paired-sessionSkill
- review-loopSkill
- review-prSkill
- code-quality-loopSkill
- guideSkill
- paired-sessionSkill
- reorganizeSkill
- review-loopSkill
- review-prSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 15 edited versions we read keep these.
1
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 60
Keep the shared review-loop config in .review-loop/config.md.
- Very specific: line 71
Start a fresh Codex session after installation (docs/install-codex.md).
- Distinctive: line 78
Run from macOS or native Windows.
“Common” is measured: kept by at least 6 in 10 of the 15 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
review-loop Guide
What review-loop Does in Codex
A review-loop request goes to the Codex review-loop skill, which resolves the entry key in
.review-loop/config.md and hands the work item to the Codex paired-session skill. That skill
runs the coordinator through plan, implementation and review. With lifecycle on, finish, polish, docs
and security follow, up to DONE. With lifecycle off, it stops after the gate; acceptance returns the uncommitted tree.
It accepts only on your explicit acceptance.
A request to review existing code hands off the same way as run --review-only, and an existing
plan becomes the work item (PLAN drafts and reviews it again). entry: legacy, asking for "the legacy
review-loop workflow" and resuming a legacy session are refused, and a failed check before the
coordinator starts refuses instead of falling back. Every run uses one mode (every sandbox, no permission probe:
permission-probe and strict mode were removed in v3.7.0; --strict only prints a NOTE).
The legacy workflow was removed in v2.13.0 (routing) and v2.13.1 (the Codex plan and execute skills, the
Codex Stage 1 workflow and its agents). Legacy session files under .review-loop/sessions/ are left on
disk and never read.
Details: docs/paired-session-migration.md.
A request to review a pull request ("review PR 123", a PR URL), a branch or
ref goes to the Codex review-pr skill, which runs the paired-session report mode
(entry: legacy and asking for the legacy review-pr are refused): it reviews it in a temporary clone with no tests
unless you confirm one, writes review-report.md, and fixes, commits or posts
nothing; posting is a separate request with a secret scan and a second
confirmation of the full body. simplify is not available there (Claude Code:
run /review-loop:code-quality-loop on the change (its POLISH-Q simplifier)).
Skills in Codex
review-loop,paired-session,review-prguide
Not on Codex:
code-quality-loop(ask review-loop to review an existing change instead: a review-only run with the quality writers on)reorganize
Usage Notes
- The entry skills load their instructions via
docs/protocol/loading.mdandscripts/read_protocol.py, shared with Claude Code. - Codex loads the skills from the installed plugin (
codex plugin add review-loop@review-loop-marketplace, seedocs/install-codex.md), not from the workspace. - macOS and native Windows: every entry refuses another host (
paired-session needs macOS or native Windows; Linux (WSL included) and other hosts are not supported). On Windows--detachis refused, Git for Windows (Git Bash) is required, and run directories and workspaces stay out of OneDrive-synced folders. On Windows the Codex skills run their commands in PowerShell as best effort; the Claude Code entry is the tested Windows path. - Hard caps — blocking PLAN/EXEC reviews HOLD at the cap;
resume --add-rounds N(1-10) continues the run. Eligible advisory-only reviews get one repair attempt per phase, then advisory acceptance, or exit at the cap without an attempt. Writer replay takes the advisory exit at any round and preserves the attempt. Blocking rounds preserve it; send-back grants a new EXEC attempt. EXEC needs a passed configured test, own run evidence and the current tree. See the advisory rules for open ledger rows. - Keep the shared review-loop config in
.review-loop/config.md; roles and models come from the paired-session operator profile; gemini (Antigravity CLIagy) is an optional third vendor for the reviewer and the gate (README.md, Configuration). Which config keys apply (round limits,docs_file,skip_quality_polish,review_focus,review_style,quality_focus,handsfree, andauto_commiton a review-only run) is listed indocs/protocol/paired-session-entry.md(Profile and settings). - A review of existing code is a review-only run. With lifecycle on,
acceptnormally makes one local commit (never a push);auto_commit: falsein.review-loop/config.mdkeeps the accepted change uncommitted. Lifecycle off stops after the gate; acceptance returns the uncommitted tree.
Troubleshooting
- The skills are missing right after an install. A fresh Codex session is what loads the plugin's skills.
Start a fresh Codex session after installation (
docs/install-codex.md). - A slash command does nothing (
Unrecognized command). Slash commands such as/review-loop:paired-sessionare Claude Code only; Codex matches skills by their description, in natural language only. Ask in plain words, for example "run review-loop on this branch", "review PR 123" or "use paired-session for this task". --detachis refused on Windows. A headless session is not supported there. Drop the flag and use an interactive session.- An entry refuses with
paired-session needs macOS or native Windows. Linux (WSL included) is not supported. Run from macOS or native Windows.
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.

