verify-pr

A process for checking whether a pull request’s description, commits, and plans match the code that was actually changed. A pull request is a proposed set of changes submitted for review.

In plain words
What is it for?
Use it to verify pull-request claims using Git changes, pull-request details, plans, and repository files.
Why use it?
It replaces unsupported claims with evidence from the repository and checks behavior rather than relying on filenames or labels. This helps reviewers determine whether the proposal is accurately described.

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

Made for: Claude Code.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,969 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00007 $0.01969
Opus 5 $0.00003 $0.00984
Sonnet 5 $0.00001 $0.00394
Haiku 4.5 $0.00001 $0.00197

Measured 2d ago against content hash 217f10018be6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify-pr 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 2d 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.

Origin

This is a copy

100% identical to verify-pr — 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.

.claude/commands/verify-pr.md · 325 lines

How it starts

The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task: Verify Pull Request Claims

PR to verify: $ARGUMENTS

Purpose: Verify that a PR's description, commits, and plan match actual implementation.

Core 4 Foundation:

  • Context: PR metadata + git changes + plan documents
  • Model: Semantic verification capabilities
  • Prompt: This systematic verification process
  • Tools: Git commands, gh CLI, file operations

Instructions

You are verifying a pull request. Check that claims in PR description, commits, and plans match actual code changes.

Core Principles

  1. Evidence before claims: Never mark verified without git command output proving it
  2. Verify behavior, not names: Check what code DOES. Different filenames can provide same functionality.
  3. Counter-evidence first: Define what would disprove claim BEFORE checking
  4. Cross-reference patterns: If comparing implementations, check what feature IS first

Step 1: Identify PR and Extract Claims

Determine PR Type

The argument could be:

  • Branch name: cursor/implement-plan-from-cu-plan-md-11ba
  • PR number: #7 or 7
  • Comparison: main...feature-branch

Commands to identify:

# If branch name given, check if it exists
git show-ref --verify refs/heads/$ARGUMENTS 2>/dev/null || git show-ref --verify refs/remotes/origin/$ARGUMENTS

# If looks like PR number, try gh
gh pr view $ARGUMENTS 2>/dev/null

# Get comparison syntax
git log --oneline main...$ARGUMENTS | head -10

Extract Claims

From PR description (if available):

gh pr view $ARGUMENTS --json body -q .body

From commit messages:

git log --format="%s%n%b" main...$ARGUMENTS

From referenced plan documents:

# Look for plan references in commits or PR description
git log main...$ARGUMENTS | grep -i "plan\|spec\|requirement"

Common claim patterns to extract:

  • "Adds feature X"
  • "Fixes bug Y"
  • "Implements Z from plan"
  • "Includes tests"
  • "Updates documentation"
  • "Breaking change"
  • "Closes #123"

Read the full file on GitHub · 325 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. 2d ago First seen · 325 lines · 7 tokens per session scan A 217f10018be6

Subscribe to this mod's changes

verify-pr is a command published in the GitHub repository basher83/agent-auditor (5 stars, last pushed 6mo ago), licensed MIT. It adds 7 tokens to every session and 1,969 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to verify-pr, differing in 0 lines, and is treated as a copy.