review-squad: Instructions file for Claude Code

CLAUDE.md

review-squad CLAUDE.md is an instructions file for Claude Code from 2389-research/review-squad. It costs 644 tokens per session, scanned A, original, MIT.

A review system that sends several kinds of reviewers to inspect a project and combines their findings into reports. Its reviewers include specialists, first-time visitors, and people checking specific user tasks.

In plain words
What is it for?
Use it for expert audits, first-impression testing, launch or health reviews, and checking flows such as finding prices, subscribing, or completing checkout.
Why use it?
One review may miss problems that another perspective would notice, such as accessibility issues, newcomer confusion, or a broken checkout flow.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions subagents.

This is 2389-research/review-squad's own configuration. It tells Claude Code how to work on review-squad itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything review-squad configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 2389-research/review-squad. 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/2389-research/review-squad/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/2389-research/review-squad

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.

agentmods badge for review-squad CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/2389-research/review-squad/claude-md/github.svg)](https://agentmods.dev/instructions/2389-research/review-squad/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/2389-research/review-squad/claude-md"><img src="https://agentmods.dev/badge/instructions/2389-research/review-squad/claude-md/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-squad CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/2389-research/review-squad/claude-md"><img src="https://agentmods.dev/badge/instructions/2389-research/review-squad/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 644 This file is loaded in full into every session.
When invoked 644 The same file — it is already loaded in full.
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 $0.00644 $0.00644
Opus 5 $0.00322 $0.00322
Sonnet 5 $0.00129 $0.00129
Haiku 4.5 $0.00064 $0.00064

Measured 9d ago against content hash b118302bcb52, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-squad CLAUDE.md 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 9d 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.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Squad Plugin

Overview

Dispatch panels of specialized subagents to review projects from multiple angles. Each skill sends a different type of reviewer at your project — experts, everyday users, task-oriented visitors, or insufferable pedants.

Skills Included

review-squad:experts

Multi-perspective expert audit. Dispatches parallel specialist agents (SEO, accessibility, security, performance, etc.) with project-type-specific default panels. Results consolidated into severity-ranked report.

Trigger keywords: review, audit, launch review, health check, pre-launch, post-refactor

review-squad:normies

First-time visitor experience testing. Dispatches personas across a sophistication spectrum (senior dev → grandparent) who land on the site cold and report confusion, friction, and first impressions.

Trigger keywords: first impressions, do people understand, newcomer experience, landing page clarity

review-squad:regulars

Task-completion verification. Dispatches personas with specific goals (find pricing, subscribe, checkout) who navigate the site like real users and report pass/fail on each flow.

Trigger keywords: smoke test, does it work, user flows, end-to-end, task completion

review-squad:well-actually

Pedantic nitpick review. Dispatches insufferable personas (Typographer, Grammarian, HN Commenter, Pixel Cop, etc.) who find the things professional reviewers skip but opinionated people on the internet will roast you for.

Trigger keywords: nitpick, polish, roast, what did I miss, hacker news, pedantic

Shared Patterns

Browser MCP

Three of the four skills (normies, regulars, well-actually) use browser MCP tools to interact with a running site. Ensure a dev server is running before dispatching these agents.

Sequential vs Parallel Dispatch

  • experts: Parallel dispatch (agents read code independently)
  • normies: Sequential (shared browser instance)
  • regulars: Sequential (shared browser instance)
  • well-actually: Sequential for browser-using agents; code-only agents can run in parallel

Read the full file on GitHub · 58 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. 9d ago First seen · 58 lines · 644 tokens per session scan A b118302bcb52

Subscribe to this mod's changes

review-squad CLAUDE.md is an instructions file published in the GitHub repository 2389-research/review-squad (12 stars, last pushed 2mo ago), licensed MIT. It adds 644 tokens to every session, about $0.0032 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens