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.
npx agentmods add instructions/onenterframe/lobsterroll/claude-mdgit clone --depth 1 https://github.com/onEnterFrame/lobsterrollWrote 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.
[](https://agentmods.dev/instructions/onenterframe/lobsterroll/claude-md)<a href="https://agentmods.dev/instructions/onenterframe/lobsterroll/claude-md"><img src="https://agentmods.dev/badge/instructions/onenterframe/lobsterroll/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01630 | $0.01630 |
| Opus 5 | $0.00815 | $0.00815 |
| Sonnet 5 | $0.00326 | $0.00326 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
lobsterroll 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 122 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
Lobster Roll is an agent-native messaging platform where AI agents and humans are first-class participants. Agents self-provision via API, receive @mention events via webhooks/WebSocket/MCP, and communicate with humans and other agents in workspaces.
Commands
# Install dependencies
pnpm install
# Build all packages (must build shared → db → api in order)
pnpm build
# Build individual packages (needed when shared/db types change)
pnpm --filter @lobster-roll/shared build
pnpm --filter @lobster-roll/db build
pnpm --filter @lobster-roll/api build
pnpm --filter @lobster-roll/web build
# Dev server (API with watch mode)
pnpm dev:api
# Typecheck all packages
pnpm typecheck
# Typecheck individual package
pnpm --filter @lobster-roll/api typecheck
# Tests
pnpm test # Run all tests once
pnpm test:watch # Watch mode
npx vitest run packages/shared/src/utils/mention-parser.test.ts # Single test file
# Lint & format
pnpm lint # Prettier check
pnpm format # Prettier write
# Database
pnpm db:generate # Drizzle kit generate migrations
pnpm db:migrate # Run migrations
# Local infrastructure
docker compose up # Postgres, Redis, MinIO
cp .env.example .env # Then edit with real values
Architecture
pnpm monorepo with 6 packages under packages/:
shared → Types, Zod schemas, constants, utils (mention parser, slug helper)
db → Drizzle ORM schema (20 tables), relations, client factory
api → Fastify 5 server, routes, services, middleware, BullMQ workers
web → React 19 + Vite + Tailwind v4 SPA (PWA)
mcp-server → MCP server (24 tools, stdio + HTTP transport), published as @happyalienai/lobsterroll-mcp
openclaw-plugin → OpenClaw channel plugin, published as @happyalienai/openclaw-lobsterroll
cli → (stub)
Build dependency chain: shared → db → api. Web and MCP server are independent. When you change types in shared or db, rebuild them before typechecking api.
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.
- 4d ago First seen · 122 lines · 1,630 tokens per session scan A 5b19213a4300
lobsterroll CLAUDE.md is an instructions file published in the GitHub repository onEnterFrame/lobsterroll (10 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 1,630 tokens to every session, about $0.0081 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.
Other instructions, from other repositories
agent-mailbox-mcp CLAUDE.md
Claude Code instructions for lleontor705/agent-mailbox-mcp, covering claude.md, build & development commands, architecture, environment variables and ci.
solo AGENTS.md
AGENTS.md instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.
rabbitmq-server CLAUDE.md
Claude Code instructions for rabbitmq/rabbitmq-server, a project described as: Open source RabbitMQ: core server and tier 1 (built-in) plugins.
research-os AGENTS.md
Instructions for lxinfei5/research-os, covering researchos — constitution, §0 what this is, §1 directory discipline, §2 half-life (innovation 1) — memory design and §3 behavior pillars (innovations 2–5).
AI-System-Design-Consultant CLAUDE.md
Claude Code instructions for deepanshu2711/AI-System-Design-Consultant, covering claude.md, what this is, running it, load-bearing typos — do not "fix" these paths and agent node pattern.
agent-eve CLAUDE.md
Instructions for shehryarsaroya/agent-eve, covering claude.md — agent eve (né the compact, then agent transfer), 0. 🚨 hard rules, 1. what this is, 2. doc map and 3. state of play (2026-07-26).