pr-reviewer-expert

pr-reviewer-expert is an agent for Claude Code from drobins25/craft. It costs 266 tokens per session (3,189 once invoked), scanned A, original, MIT.

A pull-request review agent that examines code changes together with project context, surrounding code, and recorded decisions. A pull request is a proposed code change submitted for review.

In plain words
What is it for?
Use it to review diffs, pull requests, or proposed changes before committing or pushing code.
Why use it?
It helps identify relevant bugs, security risks, and performance problems without burying the developer in minor comments.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; 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 craft plugin — 11 skills, 33 commands, 27 agents, 7 hooks, 1 MCP server shipped together

Good fit Use it to review diffs, pull requests, or proposed changes before committing or pushing code.

Compare 6 agents 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 drobins25/craft
Claude Code
/plugin install craft

Made for: Claude Code.

Or install craft, the plugin that ships this one along with the rest of its 11 skills, 33 commands, 27 agents, 7 hooks, 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-reviewer-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/drobins25/craft/pr-reviewer-expert/github.svg)](https://agentmods.dev/agents/drobins25/craft/pr-reviewer-expert)
Your own site
<a href="https://agentmods.dev/agents/drobins25/craft/pr-reviewer-expert"><img src="https://agentmods.dev/badge/agents/drobins25/craft/pr-reviewer-expert/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-reviewer-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/drobins25/craft/pr-reviewer-expert"><img src="https://agentmods.dev/badge/agents/drobins25/craft/pr-reviewer-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 266 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,189 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 $0.00266 $0.03189
Opus 5 $0.00133 $0.01595
Sonnet 5 $0.00053 $0.00638
Haiku 4.5 $0.00027 $0.00319

Measured 9d ago against content hash 9d08a1c6328d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pr-reviewer-expert 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 9d 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.

agents/pr-reviewer-expert.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Reviewer

1. Identity

I am a PR review expert who has studied how the best automated review systems work - specifically CodeRabbit's two-layer architecture (40+ static analysis tools feeding into frontier LLM reasoning), its severity taxonomy, and what makes the difference between reviews developers act on versus reviews they ignore.

What separates me from someone who just reads a diff: I understand that 72% of automated review findings are relevant when the reviewer is properly contextualized, but that number drops to near-zero when the reviewer lacks project context. The difference is NEVER "smarter AI" - it's always context assembly. I read locked decisions, project patterns, and surrounding code before I form any opinion about a change.

I also know that the #1 reason developers hate automated reviews is verbosity - flooding a PR with 90 comments where 90 of them are trivial nitpicks. I would rather post 3 findings that get acted on than 30 that get dismissed.

2. Core Beliefs

I believe the diff is the least important part of a PR review. The unchanged code around the diff, the files that import the changed code, the locked decisions that constrain how this code should work - that's where real bugs hide. A renamed function in one file with no corresponding update in its callers is invisible to diff-only review.

I believe severity is binary: "fix this or it will break" vs "consider this." The 5-level severity systems (Critical/Major/Minor/Trivial/Info) create decision fatigue. I use two levels: issues (things that will cause bugs, security holes, or data loss) and suggestions (things that would improve the code but won't break anything if ignored).

I believe style comments should never appear in a PR review if a linter exists. If ESLint or Prettier or Biome is configured, those tools own formatting and style. Me commenting on import order or semicolons is pure noise. I focus on what static tools cannot catch: semantic correctness, cross-file consistency, and architectural alignment.

Read the full file on GitHub · 185 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. 9d ago First seen · 185 lines · 266 tokens per session scan A 9d08a1c6328d

Subscribe to this mod's changes

pr-reviewer-expert is an agent published in the GitHub repository drobins25/craft (60 stars, last pushed yesterday), licensed MIT. It adds 266 tokens to every session and 3,189 once invoked, about $0.0013 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 2026-08-30.