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 skills/wecomteam/wecom-cli/wecomcli-disknpx skills add WecomTeam/wecom-cli --skill wecomcli-diskgit 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 | $0.00303 | $0.08189 |
| Opus 5 | $0.00151 | $0.04095 |
| Sonnet 5 | $0.00061 | $0.01638 |
| Haiku 4.5 | $0.00030 | $0.00819 |
Grade A, and why
wecomcli-disk scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **CLI 报错原样转达**：命令返回明确错误码时如实告知用户并给替代建议，禁止用 curl / python 等通用手段绕过 CLI 强行完成。 Copies of this mod
1 near-identical copy found in the catalogue:
- wecomcli-disk — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.
企业微信微盘
执行任何
wecom-cli命令前，必须先读取并完成wecomcli-shared技能的公共前置检查。
资源型 skill，负责微盘文件的列出、搜索、读取信息、上传、下载、重命名与新建文件夹。
适用范围
适用
- 列出微盘最近查看的文件
- 按关键词/类型/创建者/共享空间搜索微盘文件或文件夹
- 读取微盘文件基础信息
- 上传本地文件到微盘指定文件夹
- 下载微盘文件到本地
- 重命名微盘文件
- 在微盘中新建文件夹
不适用
- 移动微盘文件或文件夹 → 告知用户暂未支持，建议前往企业微信客户端手动操作
- 删除微盘文件 / 复制微盘文件 → 告知用户暂未支持，建议前往企业微信客户端手动操作
- 删除 / 重命名微盘文件夹（
folder）、调整目录树结构 → 告知用户暂未支持，建议前往企业微信客户端手动操作 - 创建 / 删除共享空间（
space）、修改空间成员与空间设置 → 告知用户暂未支持，建议前往企业微信客户端手动操作 - 给机器人授予某空间的权限 / 把机器人加入共享空间成员 → 微盘没有该功能，任何渠道都做不到（客户端也不行）。禁止向用户提出这类建议，也不要引导用户"联系空间管理员给机器人授权"
- 修改文件分享权限、生成分享链接、撤销分享、设置访问密码 / 有效期 → 告知用户暂未支持，建议前往企业微信客户端手动操作
- 微盘文件版本管理（查看历史版本、恢复旧版本、比对版本） → 告知用户暂未支持
- 撤销 / 修改已上传的文件（覆盖上传 / 秒传 / 断点续传） → 告知用户暂未支持；如需替换，请重新走「上传文件」上传一份新文件
- 解析微盘文件的内容（正文提取、OCR、看图问答、PDF/Word/Excel 解析等） → 本 skill 负责把文件下载到本地拿
file_path - 视频 / 音频文件的转写或字幕生成 → 告知用户暂未支持
- 持续监视微盘变更 / 实时通知新文件到达 → 无法主动监视，不要承诺「有新文件时告知你」，请让用户稍后主动再次发起查询
路由决策（判断本 skill / 其他 skill）
| 用户输入信号 | 路由到 |
|---|---|
| 明确提"微盘 / 网盘 / disk / Wecom 网盘" | 本 skill |
提供 https://drive.weixin.qq.com/s?k=... 链接（微盘分享 URL） |
本 skill（作为 get / download 的 url 入参） |
提供 https://doc.weixin.qq.com/<doc|sheet|smartsheet|smartpage>/... 链接 |
对应 wecomcli-doc / wecomcli-sheet / wecomcli-smartsheet / wecomcli-smartpage |
在线文档 doc / sheet / smartsheet / smartpage 的读写内容 |
同上对应文档 skill |
| 改文档权限 / 加成员 / 改文档名（针对 doc/sheet/smartsheet/smartpage） | wecomcli-doc-manage |
注意：
doc.weixin.qq.com/page.weixin.qq.com是在线文档域名，drive.weixin.qq.com才是微盘域名，切勿混用。
文件类型枚举
doc（在线文档）、sheet（在线表格）、ppt（在线幻灯片）、collect（收集表）、mind（思维导图）、flow（流程图）、smartsheet（智能表格）、smartpage（智能主页）、journal（汇报）、pdf（PDF）、offline_word（离线 Word）、offline_excel（离线 Excel）、offline_ppt（离线 PPT）、offline_pdf（离线 PDF）、image（图片）、videoaudio（视频音频）、design（设计稿）。在线文档保持原名，离线文件用 offline_ 前缀区分。腾讯文档不在本 skill 范围，按【路由决策】表改走对应文档 skill。
在线/离线模糊时同时搜：用户说「Excel」「Word」「PPT」「PDF」等未明确在线还是离线时，
file_types同时传入在线版和离线版（如["sheet", "offline_excel"]），避免遗漏。其余类型按上方枚举名按字面对应传入即可。
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 · 390 lines · 303 tokens per session scan A ce141ab3223d
wecomcli-disk is a skill published in the GitHub repository WecomTeam/wecom-cli (2,997 stars, last pushed 7d ago), licensed MIT. It adds 303 tokens to every session and 8,189 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.