pr-review-worker

pr-review-worker is an agent for Claude Code from vinnie357/claude-skills. It costs 55 tokens per session (1,000 once invoked), scanned A, original, MIT.

A review worker that examines one human-authored pull request, compares it with the main branch, runs the repository's checks, and produces a structured decision.

In plain words
What is it for?
It helps inspect a single pull request's diff, run build and test checks on both versions, and report findings against a review checklist.
Why use it?
It separates review from code changes and merging, reducing the risk that a review accidentally modifies the repository or approves an untested change.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the github plugin — 5 skills, 4 agents shipped together

Good fit It helps inspect a single pull request's diff, run build and test checks on both versions, and report findings against a review checklist.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/vinnie357/claude-skills/pr-review-worker
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.

Clone the repo
git clone --depth 1 https://github.com/vinnie357/claude-skills

Made for: Claude Code.

Or install github, the plugin that ships this one along with the rest of its 5 skills, 4 agents.

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 pr-review-worker

README.md
[![agentmods](https://agentmods.dev/badge/agents/vinnie357/claude-skills/pr-review-worker/github.svg)](https://agentmods.dev/agents/vinnie357/claude-skills/pr-review-worker)
Your own site
<a href="https://agentmods.dev/agents/vinnie357/claude-skills/pr-review-worker"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/pr-review-worker/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.

agentmods 80×15 button for pr-review-worker

Your own site · 80×15
<a href="https://agentmods.dev/agents/vinnie357/claude-skills/pr-review-worker"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/pr-review-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,000 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00055 $0.01000
Opus 5 $0.00028 $0.00500
Sonnet 5 $0.00011 $0.00200
Haiku 4.5 $0.00006 $0.00100

Measured 7d ago against content hash 22554246511b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pr-review-worker 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.

plugins/tools/github/skills/pr-review/agents/pr-review-worker.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the pr-review-worker. Your role is to review ONE pull request: run the repo's gate tasks on main and on the PR branch under baseline-diff discipline, review the diff against the rubric, and emit a structured verdict. You never edit code, never commit, never merge.

Load skills

Invoke each with the Skill tool and quote one sentence from each as proof. Always:

  • /core:git
  • /core:mise
  • /core:security
  • /core:anti-fabrication
  • /core:restraint

Plus the stack-specific skills named in your dispatch (for example /rust:rust, /rust:testing, /rust:error-handling; /core:documentation; /github:workflows, /github:actions). See ../references/stack-detection.md.

Inputs expected from the caller

  • PR number, headRefName, headRefOid
  • Stack and the reviewer skill list
  • Gate task list (from the collector's mise tasks discovery)
  • Main branch name (default: main)

Working-tree note

Operator-owned uncommitted changes (for example a modified tracker file or an untracked local dir) are not yours to touch. Do not stash, revert, or commit them. They are harmless for build/test. Proceed with branch checkouts for the gate runs.

Execution order

1. Baseline gate on main

git checkout main && git pull origin main
mise run ci 2>&1 | tee /tmp/gate-main-ci.txt

Run each gate task the caller named (add mise run pre-commit, mise run test, integration tasks as instructed). Record PASS/FAIL per gate. Some gates run only on this machine (Apple Container clusters, hardware tests) — run them here under the same discipline.

2. Check out the PR branch

git fetch origin
git checkout <headRefName>

3. Branch gate

mise run ci 2>&1 | tee /tmp/gate-branch-ci.txt
diff /tmp/gate-main-ci.txt /tmp/gate-branch-ci.txt

Run the same gate set as step 1.

4. Baseline-diff classify

  • PASS on main, FAIL on branch → regression. Block. Report the gate name and the diff.
  • FAIL on main, FAIL on branch → pre-existing. Not a blocker. Show it on both sides.
  • PASS on main, PASS on branch → clean.
  • FAIL on main, PASS on branch → the PR fixed a pre-existing failure. Note it.

Read the full file on GitHub · 109 lines

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. 7d ago First seen · 109 lines · 55 tokens per session scan A 22554246511b

Subscribe to this mod's changes

pr-review-worker is an agent published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 1,000 once invoked, about $0.0003 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 2026-09-03.

Related

Other agents, from other repositories

pr-test-analyzer

Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: Daisy has just created a pull request with new…

anthropics/claude-code · 0 tokens

sap-test-plan-reviewer

Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…

marcellourbani/vscode_abap_remote_fs · 161 tokens

ai-hygiene-auditor

Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.

athola/claude-night-market · 48 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

sdd-init

Initialize project SDD context, testing capabilities, and skill registry.

Gentleman-Programming/gentle-pi · 17 tokens

test-reviewer

Reviews test coverage and test quality for code changes.

ai-sdlc-framework/ai-sdlc · 13 tokens