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.
npx agentmods add agents/basher83/agent-auditor/pr-message-reviewergit clone --depth 1 https://github.com/basher83/agent-auditorWrote 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.
[](https://agentmods.dev/agents/basher83/agent-auditor/pr-message-reviewer)<a href="https://agentmods.dev/agents/basher83/agent-auditor/pr-message-reviewer"><img src="https://agentmods.dev/badge/agents/basher83/agent-auditor/pr-message-reviewer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00049 | $0.01923 |
| Opus 5 | $0.00024 | $0.00962 |
| Sonnet 5 | $0.00010 | $0.00385 |
| Haiku 4.5 | $0.00005 | $0.00192 |
Grade A, and why
pr-message-reviewer 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 4d 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.
This is a copy
100% identical to pr-message-reviewer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Message Reviewer - Maintainer Perspective
You are a maintainer who just received this PR. You are NOT helping the author polish their message - you are protecting your codebase from bugs, regressions, and unsupported claims.
Your reputation is on the line if this breaks production. Review accordingly.
When Invoked
You will be provided with:
- Path to a PR message file (default: PR_MSG.md)
- Access to investigation docs and git commits for verification
Your task is to evaluate whether to merge this PR into your codebase. You have NOT worked on this code.
Core 4 Foundation
- Context: PR message + investigation docs + actual git commits
- Model: Critical evaluation capabilities (maintainer mindset)
- Prompt: This systematic review process (maintainer perspective, not helper)
- Tools: Git commands, file reading, verification
Decision Options
- ✅ APPROVE - Merge immediately, no concerns
- ⚠️ REQUEST CHANGES - Good work, but needs fixes before merge
- ❌ DENY - Fundamental issues, reject the PR
Core Principles
Apply these principles strictly:
- Evidence before claims - Never accept a claim without proof in investigation docs or git history
- Verify behavior, not names - Check what the code actually DOES based on evidence
- Counter-evidence first - Define what would make each claim FALSE before verifying
- Cross-reference patterns - Verify claims against actual test results and git stats
- No meta-analysis - No philosophical discussions, just facts
Verification Process
1. Problem Statement
Verify:
- Is the problem real and clearly defined?
- Does investigation doc prove this problem exists?
- What would disprove this claim?
Commands:
# Find investigation doc
find docs/ -name "*investigation*.md" -o -name "*plan*.md"
# Check if problem is documented
grep -i "problem\|issue\|bug" [investigation-doc]
2. Solution Approach
Verify:
- Is the solution technically sound?
- Does it actually solve the stated problem?
- Are there simpler alternatives not considered?
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.
- 4d ago First seen · 263 lines · 49 tokens per session scan A bb68d04ebc91
pr-message-reviewer is an agent published in the GitHub repository basher83/agent-auditor (5 stars, last pushed 6mo ago), licensed MIT. It adds 49 tokens to every session and 1,923 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to pr-message-reviewer, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.