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 skills add sunnoy/openclaw-plugin-wecom --skill wecom-preflightgit clone --depth 1 https://github.com/sunnoy/openclaw-plugin-wecomWrote 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/skills/sunnoy/openclaw-plugin-wecom/wecom-preflight)<a href="https://agentmods.dev/skills/sunnoy/openclaw-plugin-wecom/wecom-preflight"><img src="https://agentmods.dev/badge/skills/sunnoy/openclaw-plugin-wecom/wecom-preflight.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00073 | $0.01317 |
| Opus 5 | $0.00036 | $0.00659 |
| Sonnet 5 | $0.00015 | $0.00263 |
| Haiku 4.5 | $0.00007 | $0.00132 |
Grade A, and why
wecom-preflight 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 8d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
企业微信前置检查
本技能只用于判断当前会话能否继续使用
wecom_mcp。 在 agent sandbox 内,不要执行宿主机级别的openclaw config ...或openclaw gateway restart。 本技能不适用于发消息。用户要求“给某人/群发消息、转发、通知”时,禁止调用wecom_mcp的msgcategory;应使用 OpenClaw coremessage工具(action="send"、channel="wecom")。如果当前工具列表没有message,直接说明宿主机需要把message加入tools.alsoAllow,不要改用wecom_mcp。
⚠️ 路径与停止规则:
- 如果要读取 WeCom skill,必须直接使用
<available_skills>或skillsSnapshot中给出的精确绝对路径。- 不要猜测或改写为
/data/openclaw/skills/wecom-*、/workspace/.openclaw/skills/...、/root/.openclaw/workspace-*/.openclaw/skills/...,也不要用exec+ls/find探路。- 若
wecom_mcp返回errcode: 846609或unsupported mcp biz type,表示当前 bot 未开通该 category,不是路径、白名单或 sandbox 问题;立即停止继续read、list、find、memory fallback 探索,直接告知用户对应 category 未开通。
何时使用
在以下场景使用本技能:
- 当前会话第一次准备调用
wecom_mcp - 调用
wecom_mcp后返回tool not allowed、not permitted、permission denied - 你怀疑当前环境没有把 WeCom MCP 正确暴露给 agent
如果当前会话里 wecom_mcp 已经成功调用过一次,就不要重复执行本技能。
当前部署的正确做法
本项目的 wecom_mcp 是否可用,取决于 宿主机 OpenClaw 配置 和 sandbox 挂载,不是由 agent 自己在容器里动态修复。
因此:
- 可以继续直接调用
wecom_mcp的前提:工具已经出现在当前会话可用工具中,或你刚刚已经成功调用过 - 不可以做的事:在 sandbox 里执行
openclaw config get ...、openclaw config set ...、openclaw gateway restart - 如果工具不可用,应该停止继续试探,并明确告知用户或管理员去宿主机修复
检查流程
情况 A:wecom_mcp 已可用
满足任一条件即可视为通过:
- 当前回合工具列表里已经有
wecom_mcp - 当前会话里之前已经成功调用过
wecom_mcp
处理方式:
- 直接继续执行原始 WeCom 技能
- 不要再做额外的 shell 探测
情况 B:返回工具权限错误
如果错误类似:
tool not allowednot permittedpermission deniedunknown tool: wecom_mcp
这说明问题在 宿主机工具放行配置,不是当前业务参数错误。
处理方式:
- 立即停止继续试探
- 明确告知用户:需要在宿主机上把
wecom_mcp加入允许列表,并在必要时重启 gateway - 不要在 sandbox 内尝试修复
可对用户说明:
当前会话所在的 agent sandbox 里还不能使用 wecom_mcp。这个问题需要在宿主机 OpenClaw 配置里放行 wecom_mcp,并在必要时重启 gateway 后才会生效;我无法在当前 sandbox 内直接执行这类宿主机配置。
情况 C:返回 MCP 业务错误
如果 wecom_mcp 工具本身可调用,但返回类似下面的业务错误:
unsupported mcp biz typeerrcode: 846609
这说明:
- 工具权限通常已经没问题
- 但当前机器人或当前企业微信侧 没有开通对应 category,例如只开了
doc,没有开schedule
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.
- 8d ago First seen · 105 lines · 73 tokens per session scan A f4cdba7d7e05
wecom-preflight is a skill published in the GitHub repository sunnoy/openclaw-plugin-wecom (705 stars, last pushed 3mo ago), licensed ISC. It adds 73 tokens to every session and 1,317 once invoked, about $0.0004 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 skills, from other repositories
skill-creator
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
update-setup
A one-time setup wizard for creating a personalised upgrade skill in a nanobot agent workspace. It checks whether an upgrade skill already exists and gathers version and installation details.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
weather
Get current weather and forecasts (no API key required).
clawhub
Search and install agent skills from ClawHub, the public skill registry.