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/wecomteam/wecom-cli/agents-mdgit clone --depth 1 https://github.com/WecomTeam/wecom-cliWhat 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 | $0.03651 | $0.03651 |
| Opus 5 | $0.01826 | $0.01826 |
| Sonnet 5 | $0.00730 | $0.00730 |
| Haiku 4.5 | $0.00365 | $0.00365 |
Grade A, and why
wecom-cli 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 2d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
面向 AI Agent 与贡献者的仓库导览：快速定位关键代码、理解核心机制、正确构建与测试。 本文只描述当前实现；改动代码后若结构或机制发生变化，请同步更新本文。
项目概述
wecom-cli 是企业微信官方 CLI（Rust 实现，经 npm 包 @wecom/cli 分发），覆盖消息、邮件、在线文档、智能文档、在线表格、智能表格、待办、日程、会议、微盘、通讯录等办公能力。仓库同时内置 skills/ 下的 Agent Skills，供 AI Agent 调用 CLI 完成业务操作。
CLI 通过 discovery 协议从服务端动态下发服务目录与方法 schema，再在本地构建 clap 命令树。命令模型（按 Client::run 的调度顺序）：
wecom-cli --version | --help # 版本与帮助
wecom-cli auth <init|show> # 扩展命令：bin 侧经 ClientBuilder::command() 挂载
wecom-cli cache <status|clear> # 内建命令：discovery 缓存管理（help 中隐藏）
wecom-cli schema <list|get> # 内建命令：服务/方法 schema（help 中隐藏）
wecom-cli <service> --doc | --schema # 服务级文档（service 由 discovery 下发）
wecom-cli <service> [resource...] <method> [flags] # 远程方法调用（方法参数由 schema 生成）
wecom-cli <service> +<helper> [flags] # 本地 helper（+ 前缀，HelperRegistry 调度）
仓库结构
Cargo workspace（resolver = "3"，edition 2024）+ pnpm workspace（仅管理 packages/* 平台二进制包）：
| 路径 | 说明 |
|---|---|
crates/wecom/ |
核心库（lib）：Client/ClientBuilder、argv 调度、discovery 与缓存、schema 驱动命令树、指令处理、输出路由、沙箱 FS |
crates/wecom-cli/ |
二进制（bin）：main.rs 装配入口、auth 鉴权体系、config/env/logging、WecomBackend |
crates/wecom-transport/ |
传输层：TransportBackend trait、reqwest HTTP 后端、信封 trait、端点目录泛型、长任务轮询 |
bin/wecom.js |
npm 入口脚本：定位并 exec 当前平台的二进制 |
packages/* |
各平台 npm 二进制包（optionalDependencies 分发：darwin/linux × x64/arm64、win32-x64） |
skills/* |
内置 Agent Skills（14 个，导航见 docs/skills.md） |
docs/ |
持续维护的使用与开发文档（入口 docs/README.md） |
模块职责
crates/wecom（lib）
| 模块 | 职责 |
|---|---|
client/ |
Client/ClientBuilder（builder.rs）；run.rs 的 CliRun 负责 argv 调度；invoke.rs/upload.rs 程序化调用；custom_command.rs 扩展命令点；catalog.rs 定义 EndpointKey 内建默认与 PayloadStringReq 请求信封 |
service/ |
服务调用链：handler.rs 服务内分发（helper 优先于 method）；command/ 由 schema 构建 clap 子命令树（build.rs/schema_clap.rs）并装配请求体（assemble.rs，命名参数 + --json + --set）；execute.rs 执行与游标分页；output.rs 输出路由；preview.rs --dry-run；doc.rs --doc；alias.rs path_alias 隐藏别名；service_handle.rs/method_handle.rs 程序化句柄 |
registry/ |
discovery 服务目录、schema 拉取与缓存（<config_dir>/cache，TTL 60 秒） |
schema/ |
schema 类型、解析、TS 文档生成（ts_doc.rs） |
directive/ |
x-wecom-* 指令：UploadMedia（媒体上传）、UploadMultipart（表单上传）、Save（响应字段落盘）；请求前与响应后各收集处理一次 |
builtins/ |
媒体上传的内建实现（upload_media.rs） |
helpers/ |
Helper trait 与 HelperRegistry：以 + 前缀挂载在任意命令路径上的本地命令 |
fs/ |
沙箱文件系统 Fs（按 readable/writable roots 校验）、PathResolver 路径解析、文件名清洗 |
constants.rs |
CLI_INFO/CliInfo：编译期注入的版本信息（--version 输出与 X-WeCom-Cli-Info 请求头） |
error.rs |
lib 层统一错误（错误码段 893000–893099）；后台 errcode 经 transport 透传 |
telemetry/ |
lib 侧 telemetry 事件 |
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.
- 2d ago First seen · 141 lines · 3,651 tokens per session scan A ece3a8bc531f
wecom-cli AGENTS.md is an instructions file published in the GitHub repository WecomTeam/wecom-cli (2,997 stars, last pushed 7d ago), licensed MIT. It adds 3,651 tokens to every session, about $0.0183 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
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).
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.
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).
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.
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.