pr-review

pr-review is a command for Claude Code from basher83/agent-auditor. It costs 0 tokens per session (938 once invoked), scanned A, original, MIT.

A command for checking whether claims in a pull-request comparison document are supported by the actual code. A pull request is a proposed set of changes submitted for review before it is merged.

In plain words
What is it for?
Use it to verify factual claims in the specified comparison analysis, inspect the related implementations, and document evidence that confirms or disproves each claim.
Why use it?
It prevents a review document from relying on filenames, assumptions, or unsupported statements. Each major claim must be tested against observable code behavior and backed by the commands and results used.

Command for Claude Code

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 commands/basher83/agent-auditor/pr-review
Clone the repo
git clone --depth 1 https://github.com/basher83/agent-auditor

Made for: Claude Code.

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/commands/basher83/agent-auditor/pr-review.svg)](https://agentmods.dev/commands/basher83/agent-auditor/pr-review)
Your own site
<a href="https://agentmods.dev/commands/basher83/agent-auditor/pr-review"><img src="https://agentmods.dev/badge/commands/basher83/agent-auditor/pr-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 938 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.00938
Opus 5 $0.00000 $0.00469
Sonnet 5 $0.00000 $0.00188
Haiku 4.5 $0.00000 $0.00094

Measured 4d ago against content hash 90a24ca95415, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

.claude/commands/pr-review.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task: Verify PR Comparison Analysis Claims

Document to review: docs/plans/claude-docs-upgrade/pr-comparison-analysis.md

Success criteria: Accurate verification of factual claims through code inspection.

Failure mode to avoid: Meta-analysis without verification.

Instructions

You are reviewing a PR comparison analysis document. Your job is to verify factual claims, not provide philosophical insights.

Core Rules

  1. Evidence before claims: Never mark a claim as verified without showing the git command and output that proves it
  2. No meta-analysis: Do not write about recursive patterns, cognitive dynamics, or turtles. That's a distraction.
  3. Boring is good: Methodical verification beats sophisticated commentary
  4. Show your work: Every verification must include the command you ran
  5. Verify behavior, not names: Don't just check if a file exists - check what the code DOES. A script named differently can still fulfill the requirement. Compare functionality across PRs, not just filenames.

Required Process

For each major claim in the analysis:

  1. Extract the claim: Quote it exactly
  2. Identify what would prove/disprove it: What file/code would verify this?
  3. Define the counter-evidence: Before running commands, explicitly state: "This claim would be FALSE if I found [specific evidence]" Focus on FUNCTIONALITY, not filenames.
  4. Cross-reference if needed: If claim says "PR X missing Y but PR Z has Y", verify what Y actually IS in PR Z first, then look for equivalent functionality in PR X (any filename).
  5. Run the verification command: Use git show/diff/grep
  6. Show the evidence: Paste relevant output
  7. State verdict: ✅ Verified / ❌ Incorrect / ⚠️ Partially true
  8. Move to next claim: No commentary, just next verification

Example Verification Format

Claim: "PR #7 missing Jina Reader direct API variation"

What this means: PR #7 lacks a script that makes direct HTTP calls to r.jina.ai (not using MCP)

Read the full file on GitHub · 118 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. 4d ago First seen · 118 lines · 0 tokens per session scan A 90a24ca95415

Subscribe to this mod's changes

pr-review is a command published in the GitHub repository basher83/agent-auditor (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 938 tokens. 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.