enterprise-workflow

enterprise-workflow is a skill for Claude Code, Codex from zts212653/clowder-ai. It costs 114 tokens per session (2,317 once invoked), scanned A, original, MIT.

An automation workflow for WeCom and Lark, enterprise messaging platforms, that creates documents, tables, tasks, meetings, or a combined set of these resources. It returns links and meeting details through a callback.

In plain words
What is it for?
Creating a document, smart table, to-do item, meeting, or complete document-and-task workflow in WeCom or Lark.
Why use it?
It turns a short request into coordinated workplace resources while routing actions through the required callback service.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Creating a document, smart table, to-do item, meeting, or complete document-and-task workflow in WeCom or Lark.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zts212653/clowder-ai/enterprise-workflow
About the project

Clowder AI is a self-hosted workspace where AI agents from different model families work together as a persistent team, retaining identities, shared evidence, and memory across tasks. It is for people who want to coordinate multiple AI agents without repeatedly rebuilding their context.

zts212653/clowder-ai · 2,924 stars · on GitHub

Install

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.

Any agent
npx skills add zts212653/clowder-ai --skill enterprise-workflow
Clone the repo
git clone --depth 1 https://github.com/zts212653/clowder-ai

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for enterprise-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/zts212653/clowder-ai/enterprise-workflow.svg)](https://agentmods.dev/skills/zts212653/clowder-ai/enterprise-workflow)
Your own site
<a href="https://agentmods.dev/skills/zts212653/clowder-ai/enterprise-workflow"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/enterprise-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,317 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00114 $0.02317
Opus 5 $0.00057 $0.01158
Sonnet 5 $0.00023 $0.00463
Haiku 4.5 $0.00011 $0.00232

Measured 8d ago against content hash 4d9d8ec2112e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

enterprise-workflow 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.

cat-cafe-skills/enterprise-workflow/SKILL.md · 229 lines

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.

Enterprise Workflow — 企业 IM 工作流自动化

F162:通过厂商官方 CLI 驱动企业操作。 架构决策:ADR-029 — ActionService + CliExecutor + callback route。

两条腿并行:

  • Phase A(企业微信)wecom-cli(Rust)→ callback /api/callbacks/wecom-action
  • Phase B(飞书/Lark)lark-cli(Go,@larksuite/cli)→ callback /api/callbacks/lark-action

如何选平台

operator提到 用哪边
企微 / wecom / 企业微信 / 腾讯 IM WeCom (/api/callbacks/wecom-action)
飞书 / feishu / lark / 字节 IM Lark (/api/callbacks/lark-action)
只说"企业 IM"没指定 先问一句哪个平台;demo 场景默认 WeCom

所有操作都必须走 callback route,不要裸调 CLI(ADR-029 Decision 2)。

POST /api/callbacks/{wecom|lark}-action
Content-Type: application/json

{
  "invocationId": "<your invocationId>",
  "callbackToken": "<your callbackToken>",
  "action": "<action_name>",
  ...action-specific params
}

🟩 WeCom(企业微信)能力

操作 action 说明
创建文档 create_doc Markdown 文档
创建智能表格 create_smart_table 自定义字段 + 数据行
创建待办 create_todo 分发给指定人员
创建会议 create_meeting 预约会议,自动邀请
黄金链路 golden_chain 一句话 → 文档 + 表格 + 待办 + 会议

WeCom golden_chain 示例

{
  "action": "golden_chain",
  "docName": "Q2 产品 PRD",
  "docContent": "# Q2 产品规划\n...",
  "tableName": "Q2 任务跟踪表",
  "tasks": [
    { "content": "完成 API 设计", "assigneeUserId": "zhangsan", "remindTime": "2026-04-20 09:00:00" }
  ],
  "meetingTitle": "Q2 PRD 评审会",
  "meetingStart": "2026-04-20 14:00",
  "meetingDurationSeconds": 3600,
  "meetingInviteeUserIds": ["zhangsan", "lisi"]
}

WeCom 单独操作

// create_doc
{ "action": "create_doc", "docName": "会议纪要", "content": "..." }

// create_smart_table
{
  "action": "create_smart_table",
  "tableName": "Bug 跟踪表",
  "fields": [
    { "fieldTitle": "Bug", "fieldType": "FIELD_TYPE_TEXT" },
    { "fieldTitle": "优先级", "fieldType": "FIELD_TYPE_SINGLE_SELECT" }
  ],
  "records": [{ "Bug": "登录超时", "优先级": "P1" }]
}

// create_todo
{ "action": "create_todo", "content": "Review PRD", "followerUserIds": ["zhangsan"], "remindTime": "2026-04-20 09:00:00" }

// create_meeting
{ "action": "create_meeting", "title": "评审", "startDatetime": "2026-04-20 14:00", "durationSeconds": 3600, "inviteeUserIds": ["zhangsan"] }

Read the full file on GitHub · 229 lines

Changes

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.

  1. 8d ago First seen · 229 lines · 114 tokens per session scan A 4d9d8ec2112e

Subscribe to this mod's changes

enterprise-workflow is a skill published in the GitHub repository zts212653/clowder-ai (2,924 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 2,317 once invoked, about $0.0006 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.