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/jontsai/claude-pluginsnpx agentmods add skills/jontsai/claude-plugins/review-prWrote 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/jontsai/claude-plugins/review-pr)<a href="https://agentmods.dev/skills/jontsai/claude-plugins/review-pr"><img src="https://agentmods.dev/badge/skills/jontsai/claude-plugins/review-pr.svg" alt="Measured on agentmods" 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 | $0.00139 | $0.06562 |
| Opus 5 | $0.00069 | $0.03281 |
| Sonnet 5 | $0.00028 | $0.01312 |
| Haiku 4.5 | $0.00014 | $0.00656 |
Grade A, and why
review-pr 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 779 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Tour Guide
Generate a structured, guided tour of a Pull Request that helps reviewers understand changes efficiently. Acts as a knowledgeable guide walking someone through a codebase change.
Automatic Invocation Triggers
Claude will invoke this skill when you:
- Ask to "review PR #123" or "review this PR"
- Ask for an "adversarial review" or "what breaks in this PR" (triggers Adversarial Review posture)
- Say "walk me through this PR"
- Request "PR tour guide" or "explain this PR"
- Ask "what should I look for in this PR"
- Say "create a PR review walkthrough"
- Request "review and approve PR #123" (triggers review with approval workflow)
Two Review Postures
This skill operates in one of two postures. Choose before starting; when unsure, ask.
| Posture | Question it answers | Default for |
|---|---|---|
| Tour Guide (expository) | "What does this PR do and where should I look?" | Onboarding, explaining a change, "walk me through" requests |
| Adversarial (audit) | "What's the worst thing this PR does that the author didn't mention, and is it provably safe?" | Correctness-sensitive changes, "review and approve", anything touching data integrity / auth / migrations / money |
The two share the same mechanics (fetch diff, order files, post comments). They differ in stance: Tour Guide explains and orients; Adversarial assumes the change is wrong until proven otherwise. Default to Adversarial whenever the PR touches data integrity, authorization, tenant isolation, schema/migrations, billing, or concurrency — and always when the user asks you to approve.
Overview
This skill creates a guided tour of PR changes that:
- Orders files logically (as GitHub UI shows - depth-first with folders before files)
- Groups review points into digestible stops (no more than ~25 lines per stop)
- Provides context about why code exists and its history
- Highlights review priorities (what needs rigorous review vs. rubber-stamp)
- Uses landmarks (line numbers, class/function names) for easy navigation
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.
- 7d ago First seen · 779 lines · 139 tokens per session scan A a31c7963544b
review-pr is a skill published in the GitHub repository jontsai/claude-plugins (6 stars, last pushed 27d ago), licensed MIT. It adds 139 tokens to every session and 6,562 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
avi-pr-flow
Automate PR workflow with commit, push, create PR, and review cycle.
glab
Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.
team-review
Review changed code for reuse, quality, and efficiency using a team of persistent named reviewers. This skill should be used when the user says "team review", "review with team", or wants parallel code review with persistent team members for follow-up questions. Similar to /subagent-review but reviewers persist after…
roslyn-query
Query .NET/C# codebases using Roslyn AST analysis via dotnet run file. Use for tracing data flow, auditing API usage, finding pattern violations, or ad-hoc codebase queries.
version-bump
This skill automates version bumping during the release process for the Claude Code Handbook monorepo. It should be used when the user requests to bump versions, prepare a release, or increment version numbers across the repository.
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…