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/ruihanglix/clawcenter/agents-mdgit clone --depth 1 https://github.com/ruihanglix/clawcenterWrote 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/ruihanglix/clawcenter/agents-md)<a href="https://agentmods.dev/instructions/ruihanglix/clawcenter/agents-md"><img src="https://agentmods.dev/badge/instructions/ruihanglix/clawcenter/agents-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 | $0.01871 | $0.01871 |
| Opus 5 | $0.00936 | $0.00936 |
| Sonnet 5 | $0.00374 | $0.00374 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
clawcenter 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 5d 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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - ClawCenter (dispatch)
Project Overview
ClawCenter is a TypeScript central router/dispatcher bridging multiple WeChat accounts
to multiple AI agents (Claude Code, OpenCode, CodeBuddy, Codex, etc.). It has two
operational modes: center (dispatcher + WeChat connector + worker hub) and worker
(connects to a center, runs local agents). The codebase includes a Node.js backend
(src/) and a React web management panel (web/).
Build / Run / Test Commands
| Command | Description |
|---|---|
npm run build |
Full build: compile server (tsc) + build web frontend (Vite) |
npm run build:server |
Server only: tsc |
npm run build:web |
Web frontend only: vite build --config web/vite.config.ts |
npm run typecheck |
Type-check without emitting: tsc --noEmit |
npm run dev |
Dev server with hot reload: tsx src/index.ts start |
npm run dev:worker |
Dev worker mode: tsx src/index.ts start --worker |
npm run start |
Production: node dist/index.js start |
Testing: No test framework is configured. There are no test files or test runner. If you add tests, Vitest is the recommended choice given the Vite-based web frontend.
Linting/Formatting: No linter or formatter is configured. Follow the conventions described below to maintain consistency.
Always run npm run typecheck after making changes to verify there are no type errors.
Tech Stack
- Runtime: Node.js >= 22, ESM modules (
"type": "module") - Language: TypeScript with strict mode enabled
- Server: Fastify, Commander (CLI), ws (WebSocket)
- Frontend: React 19 + Vite + React Router DOM
- Database: sql.js (SQLite in-process WASM)
- Validation: Zod
- TUI: Ink + React (terminal UI)
- AI SDKs:
@anthropic-ai/claude-agent-sdk
Project Structure
src/
index.ts # CLI entry (Commander)
server.ts # Fastify server bootstrap
logger.ts # Logging utilities
core/
agents/ # Agent adapters (one file per agent type)
adapter.ts # AgentAdapter interface + shared types
manager.ts # Agent lifecycle management
api/routes.ts # All REST API route definitions
db/
schema.ts # SQLite schema + defaults
store.ts # Data access layer (all CRUD)
center/
dispatcher.ts # Message dispatch orchestration
hub.ts # WebSocket server for remote workers
router/ # Routing engine + hashtag parser
commands/ # System slash commands
wechat/ # WeChat API client, connector, login, CDN
worker/client.ts # Worker WebSocket client
tui/ # Terminal UI (Ink/React)
web/ # Separate Vite sub-project (management panel)
src/
pages/ # One component per page (Dashboard, Settings, etc.)
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.
- 5d ago First seen · 183 lines · 1,871 tokens per session scan A 47227ca9eee1
clawcenter AGENTS.md is an instructions file published in the GitHub repository ruihanglix/clawcenter (11 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 1,871 tokens to every session, about $0.0094 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 2026-08-30.
Other instructions, from other repositories
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).
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.
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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.