pr-agent CLAUDE.md

pr-agent CLAUDE.md is an instructions file for coding agents from The-PR-Agent/pr-agent. It costs 41 tokens per session, scanned C, original, MIT.

Instructions for Claude Code in PR Agent, an open-source tool that reviews pull requests, which are proposed code changes submitted for review. The instructions also refer to AGENTS.md.

In plain words
What is it for?
Use them when asking Claude Code to inspect or change the PR Agent project.
Why use it?
They help the coding agent follow the project’s own rules while working on the code.

Instructions file

About the project

PR-Agent is an open-source AI agent that reviews pull requests and helps with code review. Developers use it to automate review work in software repositories.

The-PR-Agent/pr-agent · 12,840 stars · on GitHub

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.

agentmods
npx agentmods add instructions/the-pr-agent/pr-agent/claude-md
Clone the repo
git clone --depth 1 https://github.com/The-PR-Agent/pr-agent

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-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/the-pr-agent/pr-agent/claude-md.svg)](https://agentmods.dev/instructions/the-pr-agent/pr-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/the-pr-agent/pr-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/the-pr-agent/pr-agent/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 This file is loaded in full into every session.
When invoked 41 The same file — it is already loaded in full.
Security scan C 1 finding. Scan, not verified.
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 $0.00041 $0.00041
Opus 5 $0.00020 $0.00020
Sonnet 5 $0.00008 $0.00008
Haiku 4.5 $0.00004 $0.00004

Measured 5d ago against content hash c608b7d7bf48, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

pr-agent CLAUDE.md scanned grade C 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 5d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- AGENTS.md is the single source of truth for repository-wide agent guidance. Claude Code-specific instructions, if any, belong below this line. -->
CLAUDE.md · 6 lines

What it actually says

CLAUDE.md

@AGENTS.md

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. 5d ago First seen · 6 lines · 41 tokens per session scan C c608b7d7bf48

Subscribe to this mod's changes

pr-agent CLAUDE.md is an instructions file published in the GitHub repository The-PR-Agent/pr-agent (12,840 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.