Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mthines/agent-skillsnpx agentmods add skills/mthines/agent-skills/pr-reviewWrote 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/mthines/agent-skills/pr-review)<a href="https://agentmods.dev/skills/mthines/agent-skills/pr-review"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/pr-review/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/mthines/agent-skills/pr-review"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.03508 |
| Opus 5 | $0.00039 | $0.01754 |
| Sonnet 5 | $0.00016 | $0.00702 |
| Haiku 4.5 | $0.00008 | $0.00351 |
Grade A, and why
pr-review 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pr-review — one-shot read-only PR review
This is the thin entry point the pr-reviewer agent's own
documentation already promises (Trigger with /pr-review <PR-URL|#n>), and it does exactly one
thing: dispatch that agent at a PR and report what came back.
It never applies a finding, never pushes, and never resolves a thread. That is the whole distinction from its neighbours, and it is the reason to reach for this command rather than one of them: you get a review, and your working tree is exactly where you left it.
Contents
- Operations
- Step 0: Parse the argument
- Step 1: Resolve the PR
- Step 2: Dispatch the agent
- Step 3: Report
remember— write a maintainer relevance rule- Which review command do I want?
- Hard rules
Operations
Parse the first token of $ARGUMENTS.
| First token | Operation | Runs |
|---|---|---|
remember |
memory write | one mcp__lorekit__memory_write, no review |
| anything else (or empty) | review | one pr-reviewer dispatch, read-only |
There is no third operation, and no mode flag that turns this command into an apply pass.
A request to fix what the review found is /review-changes, below.
Step 0: Parse the argument
Everything after the PR reference is a pass-through flag: forward it verbatim and interpret none of it. The agent owns its own flag grammar, so a flag this skill has never heard of must still reach it.
# Known agent flags, listed for the argument-hint only — NOT a validation allowlist.
# --critical --full --effort high --with a,b,c --no-holistic --no-escalate
# --no-optimize --no-standards --skip-gates --fix-links
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.
- yesterday Changed · +10 lines 9fe06fb06d47
- 5d ago First seen · 268 lines · 78 tokens per session scan A 76b7bc0ed49c
pr-review is a skill published in the GitHub repository mthines/agent-skills (13 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 3,508 once invoked, about $0.0004 per session on Opus 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 2026-09-04.
Other skills, from other repositories
git-workflow
Git best practices, branching strategies, commit conventions, and code review patterns.
azure-repos
Expert knowledge for Azure Repos development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. Use when managing Git/TFVC repos, branch/PR policies, CLI/IDE integrations, CodeQL/scanning, or…
gitlab-api
Fetches and analyzes GitLab merge request (MR) comments, metadata, and review feedback using authenticated API calls. Capabilities include fetching comment threads, retrieving reviewer feedback, filtering unresolved discussions, and generating MR activity reports. Use when the user asks about GitLab MR comments, code…
mx-pr
Draft a pull request from the feature spec and git log, run an autonomous commit-history cleanup (content check), then publish to GitHub or GitLab (Bitbucket experimental) — or hand off. Use when a feature branch is ready for PR, standalone or from mx-flow. Usage: /mx-pr [name].
mx-commit
Commit all pending changes as one commit per logical concern, following the project's message convention (type prefix, 50-char subject, English). Use when the working tree may hold several changes or the convention must be enforced; a single trivial change can use plain git commit. Usage: /mx-commit [--auto].
create-pr
Opens (or updates) a pull request with a conventional title, an evidence-backed description, and a real verification checklist — resolving the base branch from evidence, attaching screenshots via the GitHub CLI when the change is visible in the UI, and asking rather than guessing at every genuine judgment call. Use…