agent-rack: Instructions file for Claude Code

CLAUDE.md

agent-rack CLAUDE.md is an instructions file for Claude Code, Codex from lakpriya1s/agent-rack. It costs 6,117 tokens per session, scanned A, original, MIT.

Repository instructions for agent-rack, an npm package and MCP server that lets AI coding tools start and control other local coding agents.

In plain words
What is it for?
Use them when working on agent-rack, including installing dependencies, running one test file or test case, and exercising the code you changed.
Why use it?
They give an AI coding assistant the commands and project context needed to build, test, type-check, and run the project after changes.

Instructions file for Claude CodeCodex

Written for Claude Code and Codex: Claude Code plugin machinery, but also runs codex exec. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is lakpriya1s/agent-rack's own configuration. It tells Claude Code and Codex how to work on agent-rack 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 agent-rack configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lakpriya1s/agent-rack. 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/lakpriya1s/agent-rack/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/lakpriya1s/agent-rack

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 agent-rack CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lakpriya1s/agent-rack/claude-md.svg)](https://agentmods.dev/instructions/lakpriya1s/agent-rack/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lakpriya1s/agent-rack/claude-md"><img src="https://agentmods.dev/badge/instructions/lakpriya1s/agent-rack/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,117 This file is loaded in full into every session.
When invoked 6,117 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 $0.06117 $0.06117
Opus 5 $0.03059 $0.03059
Sonnet 5 $0.01223 $0.01223
Haiku 4.5 $0.00612 $0.00612

Measured 7d ago against content hash f8b127bcd39c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agent-rack 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 7d 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 · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

agent-rack is an MCP (Model Context Protocol) server, published to npm, that exposes local CLI AI coding agents (claude, codex, opencode, agy) as MCP tools, so any MCP client (Claude Desktop, Cursor, Antigravity, VS Code) can spawn and drive them as sub-agents. The same package also ships a Commander CLI, an ink/React terminal dashboard, and a Claude Code plugin (plugins/agent-rack) with skills that wrap the tools.

Commands

pnpm install
pnpm build          # tsc: compiles src/ -> dist/ (bin/agent-rack.js runs the compiled output)
pnpm dev            # tsx watch src/index.ts, for iterating without a build step
pnpm start          # tsx src/index.ts, one-shot run without a build

pnpm test           # vitest run — src/**/*.test.ts only (see vitest.config.ts)
pnpm test:watch     # vitest watch mode
pnpm typecheck       # tsc -p tsconfig.test.json — typechecks sources AND tests

# Run a single test file or test:
pnpm vitest run src/engine/review.test.ts
pnpm vitest run -t "extractAndValidateReview"

# Drive the thing you just changed:
node bin/agent-rack.js agents          # after a build; probes each configured binary on $PATH
node bin/agent-rack.js config-check    # prints the fully resolved effective config
node bin/agent-rack.js dashboard       # TUI; needs a real TTY

pnpm build (tsconfig.json) excludes **/*.test.ts, docs, and src/test-helpers from the compiled output — tests never ship in dist/. pnpm typecheck (tsconfig.test.json) includes everything under src/**/* so test files are still typechecked. Any ad-hoc demo/e2e script must be excluded from tsconfig.json explicitly or it will break pnpm build.

vitest.config.ts deliberately pins include: ['src/**/*.test.ts'] — without it, leftover compiled dist/**/*.test.js from an earlier build runs every suite a second time. Consequence: a test file named *.test.tsx is silently never run. Dashboard component tests are therefore .ts files that import the .tsx components (see src/cli/dashboard/App.test.ts).

Read the full file on GitHub · 340 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. 7d ago First seen · 340 lines · 6,117 tokens per session scan A f8b127bcd39c

Subscribe to this mod's changes

agent-rack CLAUDE.md is an instructions file published in the GitHub repository lakpriya1s/agent-rack (1 stars, last pushed 1mo ago), licensed MIT. It adds 6,117 tokens to every session, about $0.0306 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

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 · 5,182 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

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

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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens