agentmods.dev

pr-review

pr-review is a skill for Claude Code from thebtf/pr-review-mcp. It costs 42 tokens per session (654 once invoked), scanned A, original, MIT.

A workflow for sending a pull request, meaning a proposed code change, to an automated review agent. It can start reviews in the background, wait for results, inspect findings, and apply code fixes.

In plain words
What is it for?
Use it to review pull requests identified by number, repository and number, or URL, then process the reported issues.
Why use it?
It removes the need to coordinate each review step manually across review tools and background agents.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the pr-review-mcp plugin — 2 skills, 3 commands, 1 agent, 1 MCP server shipped together

not rated 0repo 3mo ago A scan 42 tokens original MIT

Good fit Use it to review pull requests identified by number, repository and number, or URL, then process the reported issues.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thebtf/pr-review-mcp/pr-review
View source ↗ thebtf/pr-review-mcp
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 pr-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.

agentmods badge for pr-review

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

agentmods 80×15 button for pr-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/thebtf/pr-review-mcp/pr-review"><img src="https://agentmods.dev/badge/skills/thebtf/pr-review-mcp/pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 654 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 $0.00042 $0.00654
Opus 5 $0.00021 $0.00327
Sonnet 5 $0.00008 $0.00131
Haiku 4.5 $0.00004 $0.00065

Measured 10d ago against content hash 2b720a648eb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pr-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 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.

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/pr-review/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pr-review

Use this as the canonical consumer-facing entry for PR review workflows.

TL;DR

  • pr-reviewer is the built-in background autonomous executor agent.
  • This skill is the canonical consumer-facing entry for dispatching that agent.
  • /pr:review remains the built-in MCP prompt slash command for MCP-native flows and compatibility, but it is not the primary plugin workflow surface.

Interface boundaries (must stay explicit)

  • MCP tools: mcp__pr__pr_* (data/actions: summary, list, get, invoke, await, resolve, etc.)
  • MCP prompts / slash commands: /pr:review, /pr:review-background, /pr:setup
  • Claude skills: this file (skills/pr-review/SKILL.md) and other SKILL.md artifacts

Core workflow

  1. Parse input PR target (number, owner/repo#N, or URL).
  2. Dispatch the built-in pr-reviewer agent in background (model: sonnet).
  3. Let pr-reviewer run the full MCP-native review cycle:
    • invoke reviewers (pr_invoke)
    • await completion (pr_await_reviews / pr_poll_updates)
    • process findings (pr_list, pr_get, code fixes)
    • prefer mcp__aimux__agents for larger code changes when aimux is available in the consumer environment
    • otherwise apply fixes locally through the shipped MCP/tool surface
    • resolve fixed threads (pr_resolve)
    • hand back structured readiness report
  4. Keep merge decision outside the worker (never auto-merge).
  5. Use /pr:review only when you explicitly want the MCP prompt/slash-command path instead of the built-in plugin agent path.

Non-negotiable review rules

  • Process all severities, including MINOR and NITPICK.
  • Confidence-check every suggestion before applying.
  • Resolve each fixed thread.
  • Hand back with explicit status: READY_FOR_HUMAN_MERGE | NEEDS_USER_DECISION | BLOCKED.

Anti-patterns

  • Skill("mcp__pr__review") — wrong abstraction. That is not a Claude skill.
  • Treating /pr:review as the only plugin-facing interface — wrong. The built-in pr-reviewer agent is the primary plugin workflow surface.
  • Manual main-context review via gh pr diff/gh api ...comments as primary review path — wrong. Use the built-in agent or MCP-native prompt/tool flow.
  • Auto-merging from autonomous worker — forbidden.

Read the full file on GitHub · 52 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. 10d ago First seen · 52 lines · 42 tokens per session scan A 2b720a648eb7

Subscribe to this mod's changes

pr-review is a skill published in the GitHub repository thebtf/pr-review-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 654 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.

Code review
Related

Other skills, from other repositories

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