review

review is a skill for Claude Code, Codex from kcdjmaxx/HomarUScc. It costs 73 tokens per session (1,328 once invoked), scanned A, original, MIT.

A multi-agent code-review command that asks several specialized reviewers to examine code and combines their findings into one report ranked by severity.

In plain words
What is it for?
Use it to review uncommitted changes, a specific file, the last commit, or all changes on a branch compared with the main branch.
Why use it?
It provides separate checks for correctness, simplicity, security, and style so problems are less likely to be missed in a single review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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 skills/kcdjmaxx/homaruscc/review
Any agent
npx skills add kcdjmaxx/HomarUScc --skill review
Clone the repo
git clone --depth 1 https://github.com/kcdjmaxx/HomarUScc

Made for: Claude Code, Codex.

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 review

README.md
[![agentmods](https://agentmods.dev/badge/skills/kcdjmaxx/homaruscc/review.svg)](https://agentmods.dev/skills/kcdjmaxx/homaruscc/review)
Your own site
<a href="https://agentmods.dev/skills/kcdjmaxx/homaruscc/review"><img src="https://agentmods.dev/badge/skills/kcdjmaxx/homaruscc/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,328 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 5.1 $0.00073 $0.01328
Opus 5 $0.00036 $0.00664
Sonnet 5 $0.00015 $0.00266
Haiku 4.5 $0.00007 $0.00133

Measured 6d ago against content hash 31e22bd98559, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

skills/review/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review

Parallel code review that spawns multiple agents, each examining code from a different angle. Returns a consolidated report with findings ranked by severity.

Usage

/review                          -- review all uncommitted changes
/review src/homaruscc.ts         -- review a specific file
/review --scope last-commit      -- review the last commit
/review --scope branch           -- review all changes on the current branch vs main

How It Works

Step 1: Determine Scope

Figure out what code to review:

  • No args: git diff (unstaged) + git diff --cached (staged)
  • File path: read the file, plus its recent git history
  • --scope last-commit: git diff HEAD~1
  • --scope branch: git diff main...HEAD

If the diff is empty, tell the user there's nothing to review.

Step 2: Spawn Parallel Reviewers

Launch all reviewers simultaneously using the Agent tool. Each gets the same diff/code but checks from a different angle.

Reviewer 1: Security Sentinel

Examine this code for security issues:
- Command injection via unsanitized input to shell commands
- Path traversal in file operations
- Secrets or tokens in code
- Unsafe eval or dynamic code execution
- Missing input validation at system boundaries
- OWASP top 10 where applicable

Code to review:
<paste diff/code>

Return findings as JSON: [{"severity": "critical|high|medium|low", "location": "file:line", "issue": "description", "fix": "suggestion"}]
If no issues found, return an empty array.

Reviewer 2: Architecture & Patterns

Examine this code for architectural issues:
- Does it follow the existing patterns in the codebase?
- Are abstractions at the right level?
- Is there unnecessary coupling between modules?
- Does it respect the two-process architecture (proxy + backend)?
- Are MCP tool definitions following the established pattern?
- Is state managed correctly (server-side vs client-side)?

Code to review:
<paste diff/code>

Return findings as JSON: [{"severity": "critical|high|medium|low", "location": "file:line", "issue": "description", "fix": "suggestion"}]
If no issues found, return an empty array.

Read the full file on GitHub · 160 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. 6d ago First seen · 160 lines · 73 tokens per session scan A 31e22bd98559

Subscribe to this mod's changes

review is a skill published in the GitHub repository kcdjmaxx/HomarUScc (1 stars, last pushed 3mo ago), licensed MIT. It adds 73 tokens to every session and 1,328 once invoked, about $0.0004 per session on Opus 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 2026-08-31.