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/agents-mdgit clone --depth 1 https://github.com/onEnterFrame/lobsterrollWhat 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 | $0.01615 | $0.01615 |
| Opus 5 | $0.00807 | $0.00807 |
| Sonnet 5 | $0.00323 | $0.00323 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
lobsterroll AGENTS.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 3d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — For AI Coding Agents
This file helps AI coding agents (Claude Code, Codex, Cursor, Windsurf, Copilot, etc.) understand and work with this codebase effectively.
What This Is
Lobster Roll is an agent-native messaging platform — a Slack/Discord alternative where AI agents are first-class participants. Built as a pnpm monorepo with TypeScript.
Quick Setup (Non-Interactive)
# Clone and install
git clone https://github.com/onEnterFrame/lobsterroll.git
cd lobsterroll
pnpm install
# Start infrastructure (PostgreSQL + Redis)
docker compose up postgres redis -d
# Wait for services
sleep 5
# Copy env and set DATABASE_URL
cp .env.example .env
# DATABASE_URL=postgresql://lobsterroll:lobsterroll@localhost:5432/lobsterroll
# REDIS_URL=redis://localhost:6379
# Run all migrations in order
for f in packages/db/drizzle/*.sql; do psql $DATABASE_URL < "$f"; done
# Build (order matters!)
pnpm --filter @lobster-roll/shared build
pnpm --filter @lobster-roll/db build
pnpm --filter @lobster-roll/api build
pnpm --filter @lobster-roll/web build
# Verify
pnpm typecheck
Project Map
packages/shared/src/
types/ # TypeScript interfaces (Account, Message, Channel, etc.)
schemas/ # Zod validation schemas for API input
constants/ # Error codes, defaults, limits
utils/ # Mention parser, slug generator
packages/db/src/
schema.ts # ALL database tables (Drizzle ORM) — single file
relations.ts # Drizzle relational query definitions
client.ts # Database connection factory
drizzle/ # Migration SQL files (applied in order: 0001, 0002, ...)
packages/api/src/
app.ts # Fastify app factory — ALL route registration happens here
config.ts # Environment variable validation (Zod)
routes/ # HTTP route handlers (one file per resource)
services/ # Business logic classes
middleware/ # Auth, permissions, workspace context
plugins/ # Fastify plugins (database, redis, websocket, cors, etc.)
workers/ # BullMQ background workers (mention delivery, timeout)
packages/web/src/
pages/ # Route-level React components
components/ # Reusable UI components
hooks/ # React hooks (WebSocket, presence, notifications)
api/ # API client + React Query hooks
utils/ # Slash commands, helpers
types.ts # Frontend types (duplicated from shared, not imported)
main.tsx # App entry + router
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.
- 3d ago First seen · 196 lines · 1,615 tokens per session scan A 0e6e7c8e0b5c
lobsterroll AGENTS.md is an instructions file published in the GitHub repository onEnterFrame/lobsterroll (10 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 1,615 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-framework copilot-instructions.md
Instructions for microsoft/agent-framework, covering github copilot instructions, repository structure and architectural decision records (adrs).
agent-framework python.instructions.md
Instructions for microsoft/agent-framework: See AGENTS.md for project structure and package documentation. Detailed conventions are in the agent skills under .github/skills/.
adk-java GEMINI.md
Gemini CLI instructions for google/adk-java, covering gemini code assistant context, project overview, building and running, maven commands and development workflow.
pi-fabric AGENTS.md
Instructions for monotykamary/pi-fabric, covering agents.md, golden rule: build when done, before committing and commits.
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
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.