review

review is a skill for Claude Code from lakpriya1s/agent-rack. It costs 18 tokens per session (672 once invoked), scanned A, original, MIT.

A review command for agent-rack that asks a selected coding agent to inspect code changes without editing them.

In plain words
What is it for?
Use it to review current working-tree changes or compare a branch with a base reference, optionally with an adversarial focus or background execution.
Why use it?
It separates finding problems from fixing them, so you can review changes without risking automatic modifications.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex; mentions OpenCode.

Part of the agent-rack plugin — 11 skills shipped together

Good fit Use it to review current working-tree changes or compare a branch with a base reference, optionally with an adversarial focus or background execution.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lakpriya1s/agent-rack/review
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.

Any agent
npx skills add lakpriya1s/agent-rack --skill review
Clone the repo
git clone --depth 1 https://github.com/lakpriya1s/agent-rack

Made for: Claude Code.

Or install agent-rack, the plugin that ships this one along with the rest of its 11 skills.

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/lakpriya1s/agent-rack/review/github.svg)](https://agentmods.dev/skills/lakpriya1s/agent-rack/review)
Your own site
<a href="https://agentmods.dev/skills/lakpriya1s/agent-rack/review"><img src="https://agentmods.dev/badge/skills/lakpriya1s/agent-rack/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.

agentmods 80×15 button for review

Your own site · 80×15
<a href="https://agentmods.dev/skills/lakpriya1s/agent-rack/review"><img src="https://agentmods.dev/badge/skills/lakpriya1s/agent-rack/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 672 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00672
Opus 5 $0.00009 $0.00336
Sonnet 5 $0.00004 $0.00134
Haiku 4.5 $0.00002 $0.00067

Measured 8d ago against content hash e4fe4fb1ec48, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 8d 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.

plugins/agent-rack/skills/review/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run a read-only structured review through agent-rack's agent_review MCP tool.

Raw slash-command arguments: $ARGUMENTS

Core constraint

This command is review-only. Do not fix issues, apply patches, or make any file changes based on the findings. Your only job is to run the review and present the results.

Parsing

The first word is the agent id (e.g. claude, codex, opencode, agy). If omitted, call mcp__plugin_agent-rack_agent-rack__agent_list_available and ask the user which one to use.

Recognized flags:

  • --base <ref> → sets scope: "branch" and baseRef: <ref> (reviews the branch diff against that ref instead of the working tree)
  • --adversarialadversarial: true (skeptical, ship/no-ship stance)
  • --focus <text>focus: <text> (only meaningful with --adversarial)
  • --backgroundbackground: true (see Background handling below)
  • --timeout <seconds>timeoutSeconds: <seconds>

With no flags, this reviews the current working-tree changes in the foreground.

Execution

Call mcp__plugin_agent-rack_agent-rack__agent_review with agent and the parsed parameters.

Background handling

If background is set, the tool returns session info immediately (a sessionId, status: "running"). Tell the user the review started in the background and that they can check /agent-rack:session-status <sessionId> for the parsed result once it completes — do not poll or wait yourself.

Output rules

  • Present the verdict and summary first, then findings ordered by severity (critical → high → medium → low), then next_steps.
  • Use the file/line_start/line_end exactly as returned; 0 means whole-file or architectural, not a real line number.
  • If parseError: true, say the agent's reply couldn't be validated as structured JSON and show the raw text instead of inventing a verdict.
  • If the tool reports "Nothing to review.", say so plainly — do not spawn a review of unrelated files to have something to report.
  • CRITICAL: after presenting findings, stop. Do not make any code changes. Explicitly ask the user which findings, if any, they want addressed before touching a single file.

Read the full file on GitHub · 57 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. 8d ago First seen · 57 lines · 18 tokens per session scan A e4fe4fb1ec48

Subscribe to this mod's changes

review is a skill published in the GitHub repository lakpriya1s/agent-rack (1 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 672 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

agy-delegate

Delegate coding tasks to the Google Antigravity CLI (agy) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.

sickn33/agentic-awesome-skills · 35 tokens

cao-workflow

Author and run CAO Python workflow scripts — multi-step, parameterized, fan-out orchestrations executed by cao workflow run. Use when the user wants a repeatable multi-step job (e.g. data analysis over many files, a review pipeline, a parameterized batch). Authoring ends at a validated script file; running it is a…

awslabs/cli-agent-orchestrator · 79 tokens

aidlc-portfolio

Coordinate multiple AI-DLC workflows across repositories and Git worktrees using an evidence-backed portfolio catalog and deterministic workspace tooling. Use when initializing an AI-DLC portfolio workspace, discovering organization or business context, registering projects and dependencies, creating child intents and…

awslabs/cli-agent-orchestrator · 74 tokens

cao-plugin

Create a new CAO (CLI Agent Orchestrator) plugin. Use this skill whenever the user wants to add a plugin that reacts to CAO lifecycle or messaging events, scaffold a plugin package, understand plugin requirements, or integrate an external system (Discord, Slack, dashboards, logging, metrics) with CAO. Also use when…

awslabs/cli-agent-orchestrator · 96 tokens

agui-author

Author live dashboard UI from an agent via the emitui MCP tool. Emit one of six allow-listed components (approvalcard, choiceprompt, diffsummary, progress, metric, agentcard) with JSON props and it renders in any AG-UI client watching the fleet. Use when you want the operator to see a decision, a diff, or a status…

awslabs/cli-agent-orchestrator · 93 tokens

cao-mcp-apps

Enable, operate, and extend CAO's MCP Apps surface — the host-rendered fleet dashboard visible inside MCP App hosts (Claude Desktop, ChatGPT, VS Code Copilot, Goose, Postman). Use when the user says "enable MCP Apps in CAO", "the ui://cao views aren't rendering", "rebuild MCP Apps bundles", "add a new ui://cao/ view"…

awslabs/cli-agent-orchestrator · 137 tokens