Borrowing it
Nothing to install: this file belongs to huangjunsen0406/xiaozhi-mcphub. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/huangjunsen0406/xiaozhi-mcphub/main/AGENTS.mdgit clone --depth 1 https://github.com/huangjunsen0406/xiaozhi-mcphubWrote 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/huangjunsen0406/xiaozhi-mcphub/agents-md)<a href="https://agentmods.dev/instructions/huangjunsen0406/xiaozhi-mcphub/agents-md"><img src="https://agentmods.dev/badge/instructions/huangjunsen0406/xiaozhi-mcphub/agents-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.
<a href="https://agentmods.dev/instructions/huangjunsen0406/xiaozhi-mcphub/agents-md"><img src="https://agentmods.dev/badge/instructions/huangjunsen0406/xiaozhi-mcphub/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02838 | $0.02838 |
| Opus 5 | $0.01419 | $0.01419 |
| Sonnet 5 | $0.00568 | $0.00568 |
| Haiku 4.5 | $0.00284 | $0.00284 |
Grade A, and why
xiaozhi-mcphub 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 9d 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.
This is a copy
95% identical to mcphub AGENTS.md — 217 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xiaozhi-mcphub — Agent Guide
Authoritative instructions for AI agents and contributors working in this repo. Trust this file first; only fall back to wider search when something here is missing or contradicts the code. When you discover a contradiction, fix the code or fix this file — never let them drift.
This guide is intentionally short. It points to where the details live rather than restating them. Read the linked file when you need depth.
1. What this repo is
@huangjunsen0406/xiaozhi-mcphub is a TypeScript/Node (ESM) hub that aggregates multiple MCP (Model Context Protocol) servers behind a single HTTP surface, with a React/Vite dashboard optimized for Xiaozhi AI.
| Layer | Entry | Notes |
|---|---|---|
| Backend | src/index.ts → src/server.ts | Express + TypeORM (optional) + MCP SDK |
| Frontend | frontend/src/ | Vite + React + Tailwind, i18n via react-i18next |
| Config | mcp_settings.json | MCP server defs, users, groups, OAuth state |
| Docs | documents/ (VitePress) | Public user docs. Agent/ADR notes in docs/ |
Layout map (read the directory when you need specifics, don't expand it here):
src/{routes,controllers,services,dao,db,middlewares,models,utils,types,config,clients}/src/services/mcpService.ts— core MCP connection/lifecycle logicsrc/dao/+src/db/— dual datasource (JSON file by default, PostgreSQL whenUSE_DB=true)tests/mirrorssrc/; colocated*.test.tsalso picked uplocales/{en,fr,tr,zh}.json— i18n stringsdist/,frontend/dist/,coverage/— generated; never hand-edit
2. Workflow contract
Commands (canonical list — don't duplicate elsewhere)
| Purpose | Command |
|---|---|
| Install | pnpm install |
| Dev (both) | pnpm dev |
| Dev backend only | pnpm backend:dev |
| Dev frontend | pnpm frontend:dev |
| Lint | pnpm lint |
| Format | pnpm format |
| Test (CI mode) | pnpm test:ci |
| Test (watch) | pnpm test:watch |
| Build all | pnpm build |
| Verify dist | node scripts/verify-dist.js |
| Start prod | pnpm start |
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.
- 9d ago First seen · 202 lines · 2,838 tokens per session scan A c61af1a3b701
xiaozhi-mcphub AGENTS.md is an instructions file published in the GitHub repository huangjunsen0406/xiaozhi-mcphub (192 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,838 tokens to every session, about $0.0142 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to mcphub AGENTS.md, differing in 217 lines, and is treated as a copy.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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 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).
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.