agentmods.dev

clowder-ai: Instructions file for Claude Code

CLAUDE.md

clowder-ai CLAUDE.md is an instructions file for Claude Code from zts212653/clowder-ai. It costs 326 tokens per session, scanned A, original, MIT.

Project instructions for Clowder AI, assigning Claude the lead architecture and development role and defining safety, development, and code-quality rules. They also point to workflows such as test-driven development, which means writing tests around behavior during development.

In plain words
What is it for?
Use them when implementing or reviewing Clowder AI code: follow its feature workflow, avoid unsafe configuration or storage changes, run the stated checks, and request the required reviews.
Why use it?
They keep code changes within project safety boundaries and provide checks for file size, types, formatting, testing, review, and merging.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is zts212653/clowder-ai's own configuration. It tells Claude Code how to work on clowder-ai 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 clowder-ai configures →

not rated 3.7krepo +84 changed 24d ago A scan 326 tokens original MIT
View source ↗ zts212653/clowder-ai
About the project

Clowder AI is a self-hosted workspace where AI agents from different model families work together as a persistent team, retaining identities, shared evidence, and memory across tasks. It is for people who want to coordinate multiple AI agents without repeatedly rebuilding their context.

zts212653/clowder-ai · 3,685 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to zts212653/clowder-ai. 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/zts212653/clowder-ai/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/zts212653/clowder-ai

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 clowder-ai CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zts212653/clowder-ai/claude-md/github.svg)](https://agentmods.dev/instructions/zts212653/clowder-ai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zts212653/clowder-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/zts212653/clowder-ai/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 clowder-ai CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zts212653/clowder-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/zts212653/clowder-ai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 326 This file is loaded in full into every session.
When invoked 326 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 $0.00326 $0.00326
Opus 5.5 $0.00130 $0.00130
Sonnet 5.5 $0.00065 $0.00065
Haiku 4.5 $0.00033 $0.00033

Measured 24d ago against content hash 47dd10608b04, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

clowder-ai 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 24d 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 · 26 lines

What it actually says

Clowder AI — Claude Agent Guide

Identity

You are the Ragdoll cat (Claude), the lead architect and core developer of this Clowder AI instance.

Safety Rules (Iron Laws)

  1. Data Storage Sanctuary — Never delete/flush your Redis database, SQLite files, or any persistent storage. Use temporary instances for testing.
  2. Process Self-Preservation — Never kill your parent process or modify your startup config in ways that prevent restart.
  3. Config Immutability — Never modify cat-config.json, .env, or MCP config at runtime. Config changes require human action.
  4. Network Boundary — Never access localhost ports that don't belong to your service.

Development Flow

See cat-cafe-skills/ for the full skill-based workflow:

  • feat-lifecycle — Feature lifecycle management
  • tdd — Test-driven development
  • quality-gate — Pre-review self-check
  • request-review — Cross-cat review requests
  • merge-gate — Merge approval process

Code Standards

  • File size: review responsibilities at 200 lines; split at 350 by default or explain the structural reason to keep the unit together. Do not add per-file line-count tests.
  • Tests: see CONTRIBUTING.md; protect real behavior, reuse sufficient coverage, and choose risk-matched checks rather than repeating full gates during cleanup.
  • No any types
  • Biome: pnpm check / pnpm check:fix
  • Types: pnpm lint
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. 24d ago Changed · +1 lines · +53 tokens per session 47dd10608b04
  2. 2mo ago First seen · 25 lines · 273 tokens per session scan A ff29f2c158bd

Subscribe to this mod's changes

clowder-ai CLAUDE.md is an instructions file published in the GitHub repository zts212653/clowder-ai (3,685 stars, last pushed yesterday), licensed MIT. It adds 326 tokens to every session, about $0.0013 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 2026-08-30.

Related

clowder-ai CLAUDE.md compared with instructions from other repositories

clowder-ai CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
clowder-ai CLAUDE.mdzts212653/clowder-aiInstructions file3.7kyesterdayMITA326Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, 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