pr-review-team

pr-review-team is a skill for Claude Code from signalcompose/claude-tools. It costs 50 tokens per session (4,133 once invoked), scanned B, original, MIT.

A team-based workflow for reviewing a GitHub pull request, which is a proposed change to a codebase. It runs specialised reviewers, checks CI, applies fixes when needed, and reviews again.

In plain words
What is it for?
Use it when reviewing a pull request, including selecting parallel reviewers, running CI checks, fixing critical or important issues, and performing a follow-up review.
Why use it?
It turns review into a tracked loop so important findings, security checks, and failing tests are handled before the result is reported.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the code plugin — 3 skills, 4 commands, 1 hook shipped together

Good fit Use it when reviewing a pull request, including selecting parallel reviewers, running CI checks, fixing critical or important issues, and performing a follow-up review.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add signalcompose/claude-tools
Claude Code
/plugin install code

Made for: Claude Code.

Or install code, the plugin that ships this one along with the rest of its 3 skills, 4 commands, 1 hook.

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-team

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/signalcompose/claude-tools/pr-review-team"><img src="https://agentmods.dev/badge/skills/signalcompose/claude-tools/pr-review-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,133 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00050 $0.04133
Opus 5 $0.00025 $0.02067
Sonnet 5 $0.00010 $0.00827
Haiku 4.5 $0.00005 $0.00413

Measured 10d ago against content hash 5fdc1249b049, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

pr-review-team scanned grade B with 1 finding 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 10d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**Note**: `gh` commands rely on `sandbox.network.allowedDomains` (github.com, api.github.com) in `~/.claude/settings.json` to run inside the sandbox without prompts. Do NOT pass `dangerouslyDisableSandbox: true` defensiv
plugins/code/skills/pr-review-team/SKILL.md · 364 lines

How it starts

The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review Team

MANDATORY first step — BEFORE any Agent / Read / bash work:

bash ${CLAUDE_PLUGIN_ROOT}/scripts/pr-review-state.sh init <PR番号>

State init gives the leader (and the user reading the transcript) a visible audit trail of the review loop. Retroactively creating the state file after agents have already spawned defeats that purpose — if you skipped init, restart the loop rather than paper over it. Run init now.


MANDATORY: This skill runs a complete review-fix-re-review loop using Subagents (NOT Agent Teams).

The leader MUST:

  1. Initialize state and gather PR context (Step 1)
  2. Select and launch the parallel reviewer subagents (Step 2 — the selector decides which of the 4 run)
  3. Run CI checks via script (Step 3)
  4. Integrate results + security checklist (Step 4)
  5. If critical > 0 OR important > 0 OR security != "all_pass": enter fix loop (Step 5)
  6. Report results and cleanup (Step 6)

🔴 These steps are mandatory. The leader is accountable for completing every step — skipping is a workflow violation.

Step 1: Initialize & Identify Target PR

Initialize State

Run immediately (creates the active-review state file for audit visibility):

bash ${CLAUDE_PLUGIN_ROOT}/scripts/pr-review-state.sh init <PR番号>

Resolve PR

  • If user specified: use that number
  • Otherwise: gh pr view --json number --jq '.number' 2>/dev/null

Gather Context

  • File overview: gh pr diff <PR番号> --name-only
  • Base branch: git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|refs/remotes/origin/||' (fallback: main)
  • Test command: detect from package.json, Makefile, pytest.ini, etc.
  • Project rules: read project's CLAUDE.md if present

Note: gh commands rely on sandbox.network.allowedDomains (github.com, api.github.com) in ~/.claude/settings.json to run inside the sandbox without prompts. Do NOT pass dangerouslyDisableSandbox: true defensively — the flag forces an auto-mode-refused approval prompt that breaks the review flow (see Issue #245).

Read the full file on GitHub · 364 lines

Files

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.

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. 10d ago First seen · 364 lines · 50 tokens per session scan B 5fdc1249b049

Subscribe to this mod's changes

pr-review-team is a skill published in the GitHub repository signalcompose/claude-tools (4 stars, last pushed 13d ago), licensed MIT. It adds 50 tokens to every session and 4,133 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.