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/zhinjs/zhin/agents-mdgit clone --depth 1 https://github.com/zhinjs/zhinWhat 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 | $0.03963 | $0.03963 |
| Opus 5 | $0.01982 | $0.01982 |
| Sonnet 5 | $0.00793 | $0.00793 |
| Haiku 4.5 | $0.00396 | $0.00396 |
Grade A, and why
zhin 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zhin.js Agent Guide
本文件是本仓库给 AI 编码代理的最小入口。详细说明尽量链接到现有文档，不在这里重复展开。
项目概览
Zhin.js 是 TypeScript 多通道 IM Bot 框架（私聊、群聊、记忆、定时、通知），定位是生活/工作助手 Bot——不是 Cursor / Claude Code 类 coding agent。核心特性：插件热重载、Sandbox、Remote Console、可选 AI Agent 栈。
- 版本：4.x。默认安装仅 IM 核心（production
node_modules<10MB），AI 按需加装@zhin.js/agent+zod+ai+ 所选@ai-sdk/*（ADR 0019 安装分层）。 - 这是 pnpm workspace monorepo（pnpm 9，
pnpm-workspace.yaml为准），构建编排用 turbo。 - Node 版本要求：
^20.19.0或>=22.12.0。 - 发布流：changesets（
pnpm release记 changeset，pnpm bump升版本，pnpm pub发布）。
先读哪些文件
按这个顺序建立心智模型：
- docs/concepts/architecture.md
- docs/concepts/plugin-model.md
- docs/contributing/repo-structure.md
- README.md
- 与当前改动最近的包 README 或 docs 页面
- 符号/调用链速查：
.codegraph/MEMORY.md（CodeGraph 本地索引，需先codegraph init；不入库）
如果任务属于插件实现，再读 .github/instructions/zhin-plugin.instructions.md。
仓库结构与技术栈
- 全仓库 TypeScript（ESM），测试 Vitest，Lint ESLint 10 + typescript-eslint，构建产物经 turbo 并行。
- workspace 覆盖：
basic/*、packages/im/*、packages/console/*、packages/toolkit/*、packages/host/*、packages/game-kit、plugins/{adapters,features,games,services,utils}/*、examples/*、docs。 basic/：基础层（cli / database / logger / schedule / schema）。packages/im/：IM 核心层（adapter、agent、ai、command、component、config-yaml、core、feature-kit、isolate、kernel、mcp-feature、middleware、plugin-runtime、runtime、skill、tool、zhin 等子包）。packages/host/：Host 运行时（http / mcp / a2a；legacy router / api 插件包已删除，Console Host 由 basic/cli 装配）。packages/console/：Remote Console（Host 只提供 API，UI 在 console.zhin.dev）。packages/toolkit/：create-zhin（pnpm create zhin-app）、scaffold-wizard（配置向导）、satori、html-renderer、speech。plugins/adapters/：平台适配器（Sandbox / QQ / ICQQ / NapCat / OneBot11·12 / Discord / Telegram / Slack / KOOK / 钉钉 / 飞书 / GitHub / Email / 企微 / LINE / Satori 等）。examples/：参考实现，见下方「示例分层」。- 可选 Remote UI submodule：
zhin-console/。
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 · 164 lines · 3,963 tokens per session scan A 91706f45de43
zhin AGENTS.md is an instructions file published in the GitHub repository zhinjs/zhin (135 stars, last pushed 6d ago), licensed MIT. It adds 3,963 tokens to every session, about $0.0198 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
eve AGENTS.md
Instructions for vercel/eve, covering agents.md, about eve, repository layout, git workflow and commands.
LobsterAI AGENTS.md
AGENTS.md instructions for netease-youdao/LobsterAI, covering agents.md, instruction scope, project snapshot, cowork vs openclaw and commands.
better-chatbot AGENTS.md
AGENTS.md instructions for keinsaasforever/better-chatbot, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
AgentEval memory-benchmarks.instructions.md
Guidelines for working with AgentEval Memory module — benchmarks, reporting, HTML reports, and LongMemEval integration.
AgentEval copilot-instructions.md
Instructions for AgentEvalHQ/AgentEval, covering agenteval - ai coding agent instructions, architecture overview, environment setup, optional: secondary models for comparison and build & test commands.
AgentEval AGENTS.md
Instructions for AgentEvalHQ/AgentEval, covering agenteval development instructions, project overview, quick reference, build & test and key directories.