A command that reviews the current branch's changes against a target branch, usually main, and reports findings about correctness, edge cases, security, performance, style, and tests.

Use it to inspect commits and diffs before merging, identify must-fix issues, and report findings with specific file and line references.

It gives developers a structured review of a change set without modifying the files being reviewed.

review — Command for Claude Code by JuliusBrussee/caveman-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.

Clone the repo

git clone --depth 1 https://github.com/JuliusBrussee/caveman-code

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/juliusbrussee/caveman-code/review/github.svg)](https://agentmods.dev/commands/juliusbrussee/caveman-code/review)

Your own site

<a href="https://agentmods.dev/commands/juliusbrussee/caveman-code/review"><img src="https://agentmods.dev/badge/commands/juliusbrussee/caveman-code/review/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/juliusbrussee/caveman-code/review"><img src="https://agentmods.dev/badge/commands/juliusbrussee/caveman-code/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 374 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	$0.00017	$0.00374
Opus 5.5	$0.00007	$0.00150
Sonnet 5.5	$0.00003	$0.00075
Haiku 4.5	$0.00002	$0.00037

Measured 2mo ago against content hash aacd1b910d3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 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.

packages/coding-agent/commands/review.md · 49 lines

What it actually says

Code review the changes on the current branch.

Inputs:

Base branch: ${1:-main} (default main when no argument given).
Current branch: !git rev-parse --abbrev-ref HEAD``.

Steps:

Run !git --no-pager log --oneline ${1:-main}..HEAD`` to list commits in scope.
Run git --no-pager diff ${1:-main}...HEAD --stat for a file-level summary.
For each file with non-trivial changes, read it and evaluate:
- Correctness — does the change do what its commit message says?
- Edge cases — null/empty/large/unicode inputs, error paths.
- Security — injection sinks, unvalidated input, leaked secrets.
- Performance — quadratic loops, sync I/O on hot paths, missing caching/indexing.
- Style — matches surrounding conventions; no debug prints; comments on intent not mechanics.
- Tests — new behaviour has tests; tests fail without the change.

Produce a structured report:

## Summary
<2–4 sentence overview>

## Blockers
- <must-fix items>

## Suggestions
- <nice-to-have items>

## Nits
- <small style/typo issues>

Constraints: do not edit anything during review. Provide concrete file:line references for each finding.

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 · 49 lines · 17 tokens per session scan A aacd1b910d3a

Subscribe to this mod's changes

review is a command published in the GitHub repository JuliusBrussee/caveman-code (947 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 374 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

review next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
reviewJuliusBrussee/caveman-code	Command	947	2mo ago	MIT	A	17	Claude Code
diff-reviewcoco-research/coco	Command	785	yesterday	Apache-2.0	A	11	Claude Code
review-branchdamusix/atomic-claude	Command	115	4d ago	MIT	A	35	Claude Code
refactorRchGrav/claudebox	Command	1.2k	1mo ago	MIT	A	9	Claude Code
spec-trace-requirementsrjmurillo/ai-agents	Command	49	yesterday	MIT	A	0	GitHub Copilot
merge-conflict-analysisrjmurillo/ai-agents	Command	49	yesterday	MIT	A	0	GitHub Copilot
initazrtydxb/procoder	Command	211	11d ago	Apache-2.0	A	16	Claude Code