A repeated pull-request review process that checks changed code, architecture rules, tests, and newly introduced unused code. A pull request is a proposed code change awaiting review; architecture rules describe how parts of the project may depend on one another.

Use it to review uncommitted changes, find likely bugs and security problems, run architecture checks and tests, and detect unused code introduced by the changes.

It keeps the review going until reported problems are fixed and the checks pass, instead of leaving issues for a later step.

How cognitx-leyton/codegraph configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to cognitx-leyton/codegraph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/cognitx-leyton/codegraph/main/.claude/commands/review-pr.md

Clone the repo

git clone --depth 1 https://github.com/cognitx-leyton/codegraph

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/cognitx-leyton/codegraph/review-pr/github.svg)](https://agentmods.dev/commands/cognitx-leyton/codegraph/review-pr)

Your own site

<a href="https://agentmods.dev/commands/cognitx-leyton/codegraph/review-pr"><img src="https://agentmods.dev/badge/commands/cognitx-leyton/codegraph/review-pr/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/cognitx-leyton/codegraph/review-pr"><img src="https://agentmods.dev/badge/commands/cognitx-leyton/codegraph/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 383 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.

Model	Per session	Once invoked
Fable 5.1	$0.00014	$0.00383
Opus 5.5	$0.00006	$0.00153
Sonnet 5.5	$0.00003	$0.00077
Haiku 4.5	$0.00001	$0.00038

Measured 2mo ago against content hash c4193f57d34d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-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 2mo 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/review-pr.md · 67 lines

What it actually says

Code Review (Step 5)

Review all uncommitted changes. Fix issues found. Re-review until clean.

Review Loop

Round N:

1. Run code reviewer

Spawn the built-in feature-dev:code-reviewer agent on the changed files:

Focus on: logic bugs, edge cases, security, inconsistencies with codebase patterns
Only report HIGH confidence issues (>80%)
Include file:line references

2. Run codegraph checks

cd codegraph
.venv/bin/codegraph arch-check          # architecture conformance

Also run /dead-code to check for orphaned symbols introduced by the changes.

3. Run test suite

cd codegraph
.venv/bin/python -m pytest tests/ -q

4. Evaluate results

Result	Action
Issues found	Fix them immediately, then go to Round N+1
Tests failing	Fix the code or tests, then go to Round N+1
Arch violations	Fix or document as acceptable, then go to Round N+1
All clean	Exit loop

Exit condition

The review loop exits when ALL of these are true:

Code reviewer reports 0 high-confidence issues
arch-check passes (exit 0)
All tests pass
No new dead code introduced

Report

Review Complete
---------------
Rounds: {N}
Issues found: {total across all rounds}
Issues fixed: {total fixed}
Tests: {N} passed
Arch-check: PASS

Ready for: /commit

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.

2mo ago First seen · 67 lines · 14 tokens per session scan A c4193f57d34d

Subscribe to this mod's changes

review-pr is a command published in the GitHub repository cognitx-leyton/codegraph (12 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 383 once invoked, about $0.0001 per session on Opus 5.5. 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.

Code review ast code-analysis codebase-search cypher dependency-graph graphrag

codegraph: Command for Claude Code