review-pr

review-pr is a skill for Claude Code, Codex from JustinThomas2/agentrc. It costs 45 tokens per session (724 once invoked), scanned A, original, MIT.

A review procedure for GitHub pull requests, which are proposed code changes awaiting review. It reads the request, its diff, discussion, and linked issue before preparing feedback.

In plain words
What is it for?
It is for reviewing a pull request by checking its requirements, identifying verified issues, ranking them, and presenting a draft review.
Why use it?
It reduces false or repeated comments by checking every finding against the actual changes and existing review threads, then waiting for approval before posting.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/justinthomas2/agentrc/review-pr
Any agent
npx skills add JustinThomas2/agentrc --skill review-pr
Clone the repo
git clone --depth 1 https://github.com/JustinThomas2/agentrc

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for review-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/justinthomas2/agentrc/review-pr.svg)](https://agentmods.dev/skills/justinthomas2/agentrc/review-pr)
Your own site
<a href="https://agentmods.dev/skills/justinthomas2/agentrc/review-pr"><img src="https://agentmods.dev/badge/skills/justinthomas2/agentrc/review-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 724 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00045 $0.00724
Opus 5 $0.00023 $0.00362
Sonnet 5 $0.00009 $0.00145
Haiku 4.5 $0.00005 $0.00072

Measured 4d ago against content hash 53953361e75d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

skills/review-pr/SKILL.md · 56 lines

What it actually says

PR = $ARGUMENTS - if that reads as a literal placeholder instead of a number, use the PR number I gave when invoking this skill. If I gave none, ask for it before doing anything else.

A review is only useful if its findings are true. Never report a problem you have not verified against the actual diff, and never pad a review to look thorough - a clean PR deserves a short review saying so. Rank what you do find so the author knows what matters.

Your task

  1. Gather context, read-only:
    • gh pr view PR for the metadata, body, and linked issue
    • gh pr diff PR --patch for the full diff
    • gh pr view PR --comments for existing discussion, and gh api --method GET repos/{owner}/{repo}/pulls/PR/comments for inline review threads (file and line), so you don't repeat feedback already given at either level
    • gh issue view N for the issue the PR closes, so findings can be checked against its acceptance criteria and guardrails
  2. Review the diff on its merits:
    • verify every candidate finding against the diff (and surrounding files if needed) before it may appear in the draft; drop anything you cannot confirm
    • check the change against the linked issue's acceptance criteria and the conventions in AGENTS.md and skills/README.md
    • classify each finding: blocking, should-fix, or nit
  3. Draft the feedback: findings ranked most severe first, each tied to a specific file and hunk, each with a concrete suggested fix. If nothing survived verification, the draft says the PR looks good and why.
  4. STOP - show me the complete draft as plain text in the conversation and wait for my approval; revise until I approve. Never post anything I have not seen in chat.
  5. Post only the approved feedback with gh pr comment PR, ending the comment with the AI-attribution footer from AGENTS.md. (The posting call will ask for my approval - that is intentional; wait for it.) Post plain comments, not formal reviews: gh pr review verbs (approve / request changes) fail on the invoker's own PRs, which is the common case here.
  6. Never resolve threads, never approve or request changes, never push, never edit the PR or its body - the comment is the only mutation this skill makes.
  7. Reply with a link to the posted comment. Then STOP. When the feedback is on my own PR, I'll invoke address-feedback with PR N to act on it.
Changes

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.

  1. 4d ago First seen · 56 lines · 45 tokens per session scan A 53953361e75d

Subscribe to this mod's changes

review-pr is a skill published in the GitHub repository JustinThomas2/agentrc (2 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 724 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens