review-pr
Skill2 starsChanged 5 months agoApache-2.0View on GitHub
Use to send a GitHub PR's diff to Codex for review via `codex exec`. Required argument is the PR number. Output written to .volley/PR-REVIEW-<num>.md and shown inline. Asks for explicit user opt-in before posting as a PR comment.
185 other projects use a version of this.
Adopted by
Most recently taken up by
- jameswyse/skillstheir own version, first seen Nov 15, 2026
- connext-solutions/flowctltheir own version, first seen Nov 15, 2026
- ToolJet/ToolJettheir own version, first seen Nov 12, 2026
- tirth8205/code-review-graphtheir own version, first seen Nov 11, 2026
- data-privacy-stack/presidiotheir own version, first seen Nov 9, 2026
- pgmpy/pgmpytheir own version, first seen Nov 9, 2026
Used with
Projects with it also use diagnose-ci-failures, docs-loop 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.
zerx-labSkilldiagnose-ci-failures
Diagnose CI failures for a PR using the GitHub CLI, extract error logs, and generate a plan to fix them. Use when the user asks to check CI status, pull CI issues, triage test failures, or investigate PR build failures.
Also in 3 projects that use this
GeiserXSkilldocs-loop
Use when the user asks to audit docs, check documentation for stale claims, or verify docs against the code.
Also in 3 projects that use this
GeiserXSkillfull-loop
Drive a repository to done with sergio-loop, then keep improving it with refine-loop at a descending theta. Use only when the user explicitly invokes full-loop.
Also in 3 projects that use this
n24q02mSkillreview-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
Also in 3 projects that use this
n24q02mSkillbuild-graph
Build or update the code review knowledge graph. Run this first to initialize, or let hooks keep it updated automatically.
Also in 3 projects that use this
- +7 more from GeiserX
Other versions185 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 185
- denoland/deno★ 109ksame name
- ToolJet/ToolJet★ 41ksame name
- remix-run/remix★ 33ksame name
- tirth8205/code-review-graph★ 33ksame name
- alpinejs/alpine★ 32ksame name
- nrwl/nx★ 29ksame name
- PrefectHQ/fastmcp★ 28ksame name
- jlowin/fastmcp★ 28ksame name
- livewire/livewire★ 24ksame name
- microsoft/fluentui★ 20ksame name
175 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 repository7 other files it gives its agents.
- diagnoseSkill
- implementSkill
- review-codeSkill
- review-planSkill
- setupSkill
- statusSkill
- unlockSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 178 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
Fetch PR metadata and diff via gh: Write into .volley/ (transient, gitignored, no /tmp/ collision risk):
- Very specific: line 28
If gh is not authenticated or PR doesn't exist, surface the error and stop.
- Very specific: line 83
If y (and ONLY if y - never auto-post):
- Very specific: line 89
If verdict is APPROVE and user is the PR author: volley_next_step "merge the PR" "Codex approved.
“Common” is measured: kept by at least 6 in 10 of the 178 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
/volley:review-pr
Codex reviews a PR. You decide whether to post the review as a comment.
Steps for Claude
- Validate input. PR number is required. If missing, tell user "Pass a PR number, e.g. /volley:review-pr 123" and stop.
- Verify .volley/ is initialized and the lock allows Claude to act.
[ -d .volley ] || { echo "ERROR: .volley/ not found. Run /volley:setup first." >&2; exit 1; } [ -f .volley/STATE ] || { echo "ERROR: .volley/STATE not found. Run /volley:setup first." >&2; exit 1; } . "${CLAUDE_PLUGIN_ROOT}/scripts/lib.sh" volley_state_assert_active .volley/STATE claude || exit 1 - Fetch PR metadata and diff via gh. Write into
.volley/(transient, gitignored, no/tmp/collision risk):
IfPR_NUM=<n> gh pr view "$PR_NUM" --json title,body,baseRefName,headRefName > ".volley/pr-${PR_NUM}-meta.json" gh pr diff "$PR_NUM" > ".volley/pr-${PR_NUM}-diff.patch"ghis not authenticated or PR doesn't exist, surface the error and stop. - Build the review prompt for Codex.
You are reviewing a GitHub pull request. Be specific. Cite file paths and line numbers from the diff. PROJECT CONTEXT: before reviewing, read these files in the repo (read-only): <list every context.required file, every context.optional file that exists, and the managedCheckpoint (default .volley/CHECKPOINT.md) if it exists>. PR TITLE: <title> PR DESCRIPTION: <body> DIFF: <full diff content> Provide your review in this format: ## Verdict APPROVE | REQUEST_CHANGES | COMMENT ## Summary (2-3 sentences on what this PR does) ## Issues - (file:line — issue description) ## Nits - (file:line — minor suggestions) ## Suggestions for follow-up - (out-of-scope improvements not blocking this PR) Keep it under 800 words. - Invoke Codex via
scripts/codex-exec.sh. First resolve model, effort, local overrides and required context files exactly as in/volley:review-planstep 5 (stop if a required file is missing), then follow its step 6 with roleprReview: write the prompt to.volley/pr-<num>-review-prompt.md, then runbash "${CLAUDE_PLUGIN_ROOT}/scripts/codex-exec.sh" --prompt-file .volley/pr-<num>-review-prompt.md --out .volley/pr-<num>-review-raw.md --cwd "$(volley_repo_root)" --model <resolved> --effort <resolved> [--resume <roles.prReview.threadId>](resume percodex.review.continuityexactly as in/volley:review-planstep 6, withroles.prReview, and only when the repo identity matches). SaveSESSION_IDto.volley/local.jsonunderroles.prReview; report anyCONTINUITY=fallback:*. Surface Codex errors verbatim; never substitute a model. - Write to
.volley/PR-REVIEW-<num>.md.# Codex PR Review **PR:** #<num> — <title> **Reviewed:** <ISO timestamp> --- <Codex's response verbatim, i.e. the contents of .volley/pr-<num>-review-raw.md> - Surface the review inline.
Ask user about posting as PR comment. Output:
"Post this review as a comment on PR #
<num>? (y/n)"If
y(and ONLY if y - never auto-post):gh pr comment "$PR_NUM" --body-file ".volley/PR-REVIEW-${PR_NUM}.md"- Print the next-step block.
- If verdict is APPROVE and user is the PR author:
volley_next_step "merge the PR" "Codex approved; merge when CI is green." - Otherwise:
volley_next_step_done "Review complete. Address any issues in follow-up commits if applicable."
- If verdict is APPROVE and user is the PR author:
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.

