Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add paulinevos/claude-stuff --skill review-pull-requestgit clone --depth 1 https://github.com/paulinevos/claude-stuffWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/paulinevos/claude-stuff/review-pull-request)<a href="https://agentmods.dev/skills/paulinevos/claude-stuff/review-pull-request"><img src="https://agentmods.dev/badge/skills/paulinevos/claude-stuff/review-pull-request/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/paulinevos/claude-stuff/review-pull-request"><img src="https://agentmods.dev/badge/skills/paulinevos/claude-stuff/review-pull-request.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00069 | $0.00640 |
| Opus 5.5 | $0.00028 | $0.00256 |
| Sonnet 5.5 | $0.00014 | $0.00128 |
| Haiku 4.5 | $0.00007 | $0.00064 |
Grade A, and why
review-pull-request scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
review-pull-request
You review one PR, in its own checkout, by that project's rules — not your own taste. Read review-standards before writing findings. You plan comments; you MUST NOT post them, push, or alter the PR.
-
Read the PR and its diff. Work from the checkout path you were given.
gh pr view <n> --repo <owner/name> --json title,body,author,isDraft,baseRefName,additions,deletions,changedFiles,closingIssuesReferences gh pr diff <n> --repo <owner/name>Check the diff out locally (
gh pr checkout <n>) only when you must run something; stash first and restore the prior branch when done. -
Read the project's guideline files before judging any line. They outrank your defaults and this skill. Where a guideline and your instinct disagree, the guideline wins and the finding goes away. Note which guideline a finding rests on — a finding you cannot attribute to a guideline, a test, or a demonstrable defect is not a finding.
-
Review the diff against those guidelines, reading surrounding files for the conventions the diff should match: how siblings are structured, named and tested. A change consistent with its neighbours is correct even when you would have written it differently.
-
Check docs parity. Search the project's docs for what this change affects — behaviour, options, defaults, public API. A behavioural change that leaves the docs describing the old behaviour is a finding; so is a new public surface documented nowhere. Say which doc file is now stale.
-
Guard against scope creep. Read the issue the PR closes (
closingIssuesReferences, or an issue named in the body) and its linked discussion. Map each changed file to the issue's stated problem. Anything unexplained by the issue or the PR description is a finding: name the file and ask why it belongs, rather than asserting it does not. -
Plan the comments. Write findings to the scratchpad you were given, in the shape review-standards specifies — one entry per comment, each with file, line, severity, the guideline it rests on, and the comment as you would post it. Finish with a short summary: what the PR does, whether it does it, and the blocking findings if any.
-
Report that the scratchpad is written and stop. Do not post, approve, request changes, or push.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 46 lines · 69 tokens per session scan A 336d4debfa74
review-pull-request is a skill published in the GitHub repository paulinevos/claude-stuff (64 stars, last pushed 4d ago), licensed MIT. It adds 69 tokens to every session and 640 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-06.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
git-pr-workflows-git-workflow
Guide changes through code checks, testing, commits, and pull request preparation. Use when coordinating a complete Git workflow and verifying readiness for collaboration.