review

review is a command for coding agents from IvanLutsenko/awac-ai-agent-plugins. It costs 28 tokens per session (3,762 once invoked), scanned C, original, MIT.

A combined code-review command for checking GitHub pull requests, GitLab merge requests, branch differences, or uncommitted changes.

In plain words
What is it for?
Use it to review the current changes or compare a branch, pull request, or merge request with a chosen base.
Why use it?
It brings several review checks into one workflow so potential bugs, rule violations, and risky changes are easier to find.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the combined-review plugin — 5 skills, 1 command, 4 agents shipped together

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/ivanlutsenko/awac-ai-agent-plugins/review
Clone the repo
git clone --depth 1 https://github.com/IvanLutsenko/awac-ai-agent-plugins

Or install combined-review, the plugin that ships this one along with the rest of its 5 skills, 1 command, 4 agents.

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/commands/ivanlutsenko/awac-ai-agent-plugins/review.svg)](https://agentmods.dev/commands/ivanlutsenko/awac-ai-agent-plugins/review)
Your own site
<a href="https://agentmods.dev/commands/ivanlutsenko/awac-ai-agent-plugins/review"><img src="https://agentmods.dev/badge/commands/ivanlutsenko/awac-ai-agent-plugins/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,762 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00028 $0.03762
Opus 5 $0.00014 $0.01881
Sonnet 5 $0.00006 $0.00752
Haiku 4.5 $0.00003 $0.00376

Measured 3d ago against content hash 38935f8bb0ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

review scanned grade C with 2 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 3d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://cli.coderabbit.ai/install.sh | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Bash(gh:*), Bash(glab:*), Bash(git:*), Bash(coderabbit:*), Bash(cr:*), Bash(curl:*), Bash(python3:*), Bash(which:*), Bash(wc:*), Bash(head:*), Bash(tail:*), Bash(cat:*), Bash(find:*), Bash(grep:*), Bash(rg
plugins/combined-review/commands/review.md · 332 lines

How it starts

The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Combined Code Review

Context

  • Directory: !pwd
  • Branch: !git branch --show-current 2>/dev/null || echo "detached HEAD"
  • Has changes: !git status --porcelain 2>/dev/null | head -1 | grep -q . && echo "yes" || echo "no"

Step 0 — Read config

Check if config exists at .claude/combined-review.local.md. If it exists, read the language setting from YAML frontmatter.

If config doesn't exist, use default: language: system.

Language resolution:

  • system → detect from CLAUDE.md (look for language hints like "Отвечай", "русский", etc.) or fall back to English
  • en / ru / uk → use directly

Apply the resolved language to the final report output (Step 6). Agents work internally in English for accuracy; only the final report is translated.

Arguments

$ARGUMENTS

Finding format

CRITICAL: every finding MUST include file path and line number: path/to/File.kt:42.

Step 1 — Parse arguments

Split $ARGUMENTS into mode and options:

Mode (first argument or pair):

  • Empty → current changes (uncommitted + staged)
  • --base <branch> → current branch vs specified
  • Number (123) → PR/MR number. Detect the forge from git remote get-url origin:
    • host contains github → GitHub PR (use gh)
    • host contains gitlab → GitLab MR (use glab)
  • !123 or a .../-/merge_requests/123 URL → GitLab MR explicitly (use glab, repo = the MR's project)
  • Two branch-like arguments → diff of first relative to second (target is second)
    • feature/X feature/Y
    • feature/X to feature/Y
    • feature/X...feature/Y

Branch-like: contains /, or starts with feature/, fix/, release/, hotfix/, master, main, develop.

!N is zsh-escaped as \!N when typed — the literal mode value is !N. If gh/glab returns 404 for a bare number, you likely picked the wrong forge — re-check the origin host.

Options (after mode):

  • +comments — add comment analysis
  • +types — add type design analysis
  • +simplify — add code simplification
  • +threads — after the report, post findings as inline resolvable threads on the MR/PR (GitLab MR only; see Step 7). Opt-in — never post without this flag or an explicit request.
  • all — run all agents including optional

Read the full file on GitHub · 332 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. 3d ago First seen · 332 lines · 28 tokens per session scan C 38935f8bb0ad

Subscribe to this mod's changes

review is a command published in the GitHub repository IvanLutsenko/awac-ai-agent-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 3,762 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.