An automated pull-request review workflow that coordinates AI reviewers, processes their findings, and checks whether the project still builds.

Use it after creating a pull request or when review comments need handling, including reviews for a specific pull request or repository.

It brings review results and build verification into one process instead of requiring each review step to be managed separately.

review — Skill for Claude Code by thebtf

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.

Any agent

npx skills add thebtf/pr-review-mcp --skill review

Clone the repo

git clone --depth 1 https://github.com/thebtf/pr-review-mcp

Made for: Claude Code.

Or install pr-review-mcp, the plugin that ships this one along with the rest of its 2 skills, 3 commands, 1 agent, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/thebtf/pr-review-mcp/review/github.svg)](https://agentmods.dev/skills/thebtf/pr-review-mcp/review)

Your own site

<a href="https://agentmods.dev/skills/thebtf/pr-review-mcp/review"><img src="https://agentmods.dev/badge/skills/thebtf/pr-review-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/thebtf/pr-review-mcp/review"><img src="https://agentmods.dev/badge/skills/thebtf/pr-review-mcp/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,291 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.

Model	Per session	Once invoked
Fable 5.1	$0.00092	$0.01291
Opus 5	$0.00046	$0.00646
Sonnet 5	$0.00018	$0.00258
Haiku 4.5	$0.00009	$0.00129

Measured 11d ago against content hash 5ba27e4eb029, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

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 11d 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/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review Orchestrator

Autonomous multi-agent PR review: invoke AI agents, await their reviews, process all findings, verify build.

How It Works

This skill calls the review MCP prompt from the pr server. The prompt dynamically builds an orchestration plan with pre-fetched PR data (summary, work status, agent config). The plan includes:

Delegation instructions — create tracking tasks, spawn a background sonnet agent
Full orchestrator workflow — escape check, invoke, await, spawn workers, build/test
Worker templates — for parallel comment processing

You don't need to understand the internals — just call the prompt and follow its instructions.

Invocation

/pr:review              — Context-dependent (see below)
/pr:review 42           — PR #42 in current repo
/pr:review owner/repo#5 — Specific PR in any repo
/pr:review https://github.com/owner/repo/pull/123 — Full URL

No-argument behavior depends on current branch:

Feature branch → auto-detects the PR for this branch (single PR mode)
Main/master → processes all open PRs with unresolved review comments (batch mode, up to 20)
Main/master + no PRs with comments → processes first 5 open PRs

Workflow

Step 1: Call the MCP Prompt

Use the `review` prompt from the `pr` MCP server, passing $ARGUMENTS as the `pr` parameter.

The prompt returns a complete orchestration plan. It has two sections:

DELEGATION — instructions for YOU (the parent agent)
ORCHESTRATOR PROMPT — instructions for the background agent you'll spawn

Step 2: Follow the Delegation Plan

The delegation section tells you to:

Create 4 tracking tasks via TaskCreate:
- Preflight checks
- Wait for AI agent reviews
- Process review comments
- Build and test
Spawn a background agent via Agent(model: "sonnet", run_in_background: true) with the ORCHESTRATOR PROMPT section as its prompt.
Monitor progress — when the background agent sends progress notifications, call pr_progress_check and update your tasks accordingly.

Read the full file on GitHub · 116 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.

11d ago First seen · 116 lines · 92 tokens per session scan A 5ba27e4eb029

Subscribe to this mod's changes

review is a skill published in the GitHub repository thebtf/pr-review-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 92 tokens to every session and 1,291 once invoked, about $0.0005 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.

Code review

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

full-repo-review

Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.

notque/vexjoy-agent · 22 tokens

agent-teams-simplify-and-harden

Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…

LeoYeAI/openclaw-master-skills · 115 tokens