Paddock: Instructions file for Claude Code

CLAUDE.md

Paddock CLAUDE.md is an instructions file for Claude Code from racecraft-lab/Paddock. It costs 4,240 tokens per session, scanned A, original, MIT.

Project instructions for deploying and operating Paddock, an open-source dashboard for managing AI-agent teams and their tasks.

In plain words
What is it for?
Use it when preparing, running, or checking Paddock and its separate OpenClaw gateway service.
Why use it?
It records which worktrees, services, startup scripts, and release paths the deployment depends on.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions Codex; built for openclaw.

This is racecraft-lab/Paddock's own configuration. It tells Claude Code how to work on Paddock 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 Paddock configures →

Reuse

Borrowing it

Nothing to install: this file belongs to racecraft-lab/Paddock. 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/racecraft-lab/Paddock/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/racecraft-lab/Paddock

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 Paddock CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/racecraft-lab/paddock/claude-md/github.svg)](https://agentmods.dev/instructions/racecraft-lab/paddock/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/racecraft-lab/paddock/claude-md"><img src="https://agentmods.dev/badge/instructions/racecraft-lab/paddock/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 Paddock CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/racecraft-lab/paddock/claude-md"><img src="https://agentmods.dev/badge/instructions/racecraft-lab/paddock/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,240 This file is loaded in full into every session.
When invoked 4,240 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 $0.04240 $0.04240
Opus 5.5 $0.01696 $0.01696
Sonnet 5.5 $0.00848 $0.00848
Haiku 4.5 $0.00424 $0.00424

Measured 2mo ago against content hash 2b4c898d9dff, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Paddock 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 2mo 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 · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Paddock

Open-source dashboard for AI agent orchestration. Manage agent fleets, track tasks, monitor costs, and orchestrate workflows.

Stack: Next.js 16, React 19, TypeScript 5, SQLite (better-sqlite3), Tailwind CSS 3, Zustand, pnpm

OpenClaw Node Deployment Notes

  • These notes apply to operator-managed Paddock worktrees: <live-worktree> (live main) and <dev-worktree> (dev branch).
  • Paddock should run from racecraft-lab/Paddock main.
  • Active systemd unit: paddock.service
  • Active startup wrapper: ~/.local/bin/mc-start.sh
  • The wrapper resolves runtime secrets from the operator's configured secret manager at startup.
  • Active service worktree: <live-worktree> on main; <dev-worktree> is the development worktree on the active feature branch.
  • OpenClaw is a separate deploy surface on the operator node. The gateway should run from <openclaw-release-symlink>, which should point at the clean tagged release tree, not from a Homebrew global package path.
  • If you change startup assumptions, verify both:
    • systemctl --user status --no-pager paddock.service
    • systemctl --user status --no-pager openclaw-gateway.service

Prerequisites

  • Node.js >= 22 (LTS recommended; 24.x also supported)
  • pnpm (corepack enable to auto-install)

Setup

pnpm install
pnpm build

Secrets (AUTH_SECRET, API_KEY) auto-generate on first run if not set. Visit http://localhost:3000/setup to create an admin account, or set AUTH_USER/AUTH_PASS in .env for headless/CI seeding.

Run

pnpm dev              # development (localhost:3000)
pnpm start            # production
node .next/standalone/server.js   # standalone mode (after build)

Docker

docker compose up                 # zero-config
bash install.sh --docker          # full guided setup

Production hardening: docker compose -f docker-compose.yml -f docker-compose.hardened.yml up -d

Tests

pnpm test             # unit tests (vitest)
pnpm test:e2e         # end-to-end (playwright)
pnpm typecheck        # tsc --noEmit
pnpm lint             # eslint
pnpm test:all         # lint + typecheck + test + build + e2e

Read the full file on GitHub · 173 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. 2mo ago First seen · 173 lines · 4,240 tokens per session scan A 2b4c898d9dff

Subscribe to this mod's changes

Paddock CLAUDE.md is an instructions file published in the GitHub repository racecraft-lab/Paddock (12 stars, last pushed 4mo ago), licensed MIT. It adds 4,240 tokens to every session, about $0.0170 per session on Opus 5.5. 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 2026-09-03.

Related

Paddock CLAUDE.md compared with instructions from other repositories

Paddock CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Paddock CLAUDE.mdracecraft-lab/PaddockInstructions file124mo agoMITA4,240Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode