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/bezhai/chiwei-platform/claude-mdgit clone --depth 1 https://github.com/bezhai/chiwei-platformWrote 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/bezhai/chiwei-platform/claude-md)<a href="https://agentmods.dev/instructions/bezhai/chiwei-platform/claude-md"><img src="https://agentmods.dev/badge/instructions/bezhai/chiwei-platform/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 | $0.04886 | $0.04886 |
| Opus 5 | $0.02443 | $0.02443 |
| Sonnet 5 | $0.00977 | $0.00977 |
| Haiku 4.5 | $0.00489 | $0.00489 |
Grade A, and why
chiwei-platform 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chiwei-platform
宪法级文档（禁止修改）
MANIFESTO.md（赤尾宣言）是本项目的宪法。未经 bezhai 明确许可，任何人和任何 AI 不得修改此文件。
Monorepo，所有应用在 apps/ 下。部署在 K8s prod namespace。
项目结构
apps/
paas-engine/ # PaaS 引擎 (Go) - 管理应用构建和蓝绿部署
lite-registry/ # 泳道注册表 (Go) - Watch K8s Services，提供泳道路由数据
lark-service/ # 飞书渠道服务 (Bun/TS) - 入站 + 出站，同一镜像产出 2 个独立 Deployment（见下方映射表）
channel-server/ # QQ 渠道服务 (Bun/TS) - 同一镜像产出 2 个独立 Deployment（见下方映射表）
qq-gateway/ # QQ 官方 bot 适配 (Bun/TS) - QQ 协议 ↔ channel-server 通用协议
agent-service/ # AI 对话引擎 (Python)
api-gateway/ # 反向代理入口 (Go)
镜像与服务映射（一镜像多服务）
一个 Docker 镜像可以产出多个独立的 K8s Deployment。 它们是不同进程、不同 Pod，日志和排查必须按实际服务名来，不能混淆。
| 镜像（ImageRepo） | 产出的 K8s Deployment | 角色 |
|---|---|---|
| lark-service | lark-service | 飞书入站：websocket 长连 + webhook 路由 + 泳道交接接收端（POST /api/internal/lark/lane-inbound）+ 三个定时任务（daily-photo / daily-new-photo / emoji-sync） |
| lark-service | lark-outbound | 消费 chat_response_lark / recall_lark 两条出站队列，发飞书消息与撤回 |
| channel-server | channel-server | HTTP 服务，QQ 入站（POST /api/internal/qq/inbound，由 qq-gateway 投递） |
| channel-server | chat-response-worker | 消费 RabbitMQ 回复队列，经 qq-gateway 发 QQ 消息 |
| agent-service | agent-service | HTTP 服务，AI 对话 + world/life 引擎 |
常见错误：查 chat-response-worker 的日志时用 make logs APP=channel-server，这是错的。 chat-response-worker 是独立 Deployment，必须用 make logs APP=chat-response-worker。同理 lark-outbound 也是独立服务，飞书发不出消息要查 make logs APP=lark-outbound，不是 APP=lark-service。
核心数据流
飞书消息处理
入站走 websocket 长连，不经 api-gateway：lark-service 主动连飞书开放平台，事件由飞书推过来。
长连对同一 app_id 是随机投递，所以持连的是单副本 Deployment，且只有 prod 部署 + LARK_DIRECT_INGRESS=true 才连（泳道部署不连，消息由 prod 带 x-ctx-lane 打一次内部 HTTP 交接过来，lane-sidecar 选路）。
/webhook/{bot}/{event,card} 路由仍然注册着，走 api-gateway 进来，是长连之外的被动入口。
飞书 --websocket 长连--> lark-service:3000 (投影 common 口径 + 规则引擎 + 决定 lane)
→ RabbitMQ: chat_request 队列
→ agent-service:8000 (AI 对话, 工具调用)
→ RabbitMQ: chat_response_lark / recall_lark 队列
→ lark-outbound → 飞书
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 · 229 lines · 4,886 tokens per session scan A d608bd14d747
chiwei-platform CLAUDE.md is an instructions file published in the GitHub repository bezhai/chiwei-platform (20 stars, last pushed yesterday), licensed MIT. It adds 4,886 tokens to every session, about $0.0244 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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.