os-workflow SKILL.md skillA
os-workflow from cronusl-1141/ai-company is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add cronusl-1141/ai-company/os-workflow@git:20261027.8c6e2aePins git:20261027.8c6e2ae in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- cronusl-1141/ai-company
- Path
plugin/skills/os-workflow/SKILL.md- Versions recorded
- 8
- Latest version
- git:20261027.8c6e2ae, committed Oct 27, 2026
- First version recorded
- Jul 28, 2026
- Size
- 7,743 bytes
- Repository stars
- 374
- License
- MIT
AI Team OS 里用 CC 内置 Workflow 的两件事：产出回写 OS 的标准模板（§1-2、§4），以及审查分级与派工档位纪律（§3/§3.1）。准备调用 Workflow 编排子 agent 时，或要判定一件事该按 L0/L1/L2 哪一档审查（含「这活要不要开 workflow」）时使用。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# OS Workflow — 用 CC 工作流，但让产出回流 OS
## 背景
调用 Workflow 后，每个内部 agent 会被 hook 自动注册成一个 OS 团队（`workflow-<wf_id>`，
一次 workflow = 一个团队）。追踪是自动的，但**工作内容不会自己入库**——下面两件事必须你做。
## 1. 总任务上墙（Leader 职责）
调用 Workflow **前**用 `task_create` 把这次工作方向登记上墙并置 running（§2 的回写指令要把它的 id
插进每个 agent 的 prompt，事后补建来不及），完成后 `task_update` 置 completed 并填 result。
## 2. 在每个 workflow agent 的 prompt 里嵌入「回写指令」
把下面这段**粘进你写的 workflow 脚本里每个 `agent()` 的 prompt 末尾**（已验证 workflow
agent 能调 OS 的 MCP 工具 + HTTP API，非沙盒）：
```
【回写 OS（收尾必做）】
1. ToolSearch 加载：select:mcp__ai-team-os__task_memo_add,mcp__ai-team-os__report_save
2. 完成本职工作后：
- task_memo_add(task_id="<总任务id>", content="<这步干了啥+关键结论>", memo_type="progress")
- 重要产出再 report_save(...) 落库，并把 report_id 写进 memo
3. 你在项目目录运行，MCP 自动带项目头，无需关心端口/项目 id。
```
在脚本里把 `<总任务id>` 用第 1 步 `task_create` 拿到的 id 通过 prompt 字符串插值传进去。
### 脚本写法示例
```js
// Leader 先 task_create 拿到 taskId（OS MCP），再写 workflow：
const WRITEBACK = `\n【回写 OS（收尾必做）】\n1. ToolSearch: select:mcp__ai-team-os__task_memo_add\n2. 完成后 task_memo_add(task_id="${taskId}", content="...", memo_type="progress")\n3. 项目目录运行，MCP 自动带项目头。`
const r = await agent('你的实际任务……' + WRITEBACK, { schema, label })
```
## 3. 模型档位纪律
…Read the whole file at its exact version.
How to install
mdr add cronusl-1141/ai-company/os-workflow@sha256:e3cdfe5b1c5dcaa4The line at the top of this page pins the label git:20261027.8c6e2ae, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_fncphpmmnn5ykvst)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Jul 28, 2026 and Oct 27, 2026, about one every 13 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261027.8c6e2ae latest | 2026-10-27 | 8c6e2ae | 7,743 B | A | view · diff |
| git:20260923.533b3dd | 2026-09-23 | 533b3dd | 7,714 B | A | view · diff |
| git:20260918.dd60e97 | 2026-09-18 | dd60e97 | 8,103 B | A | view · diff |
| git:20260914.98e9601 | 2026-09-14 | 98e9601 | 8,109 B | A | view · diff |
| git:20260907.5bd2417 | 2026-09-07 | 5bd2417 | 8,456 B | A | view · diff |
| git:20260902.0c9b9a4 | 2026-09-02 | 0c9b9a4 | 4,625 B | A | view · diff |
| git:20260731.7b33b68 | 2026-07-31 | 7b33b68 | 4,231 B | A | view · diff |
| git:20260728.607df71 | 2026-07-28 | 607df71 | 3,596 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7743 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
cronusl-1141/ai-company · 374 stars · license MIT · pushed 2026-10-27 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_fncphpmmnn5ykvst GET https://markdownregistry.com/api/v1/resolve?ref=cronusl-1141/ai-company/os-workflow GET https://markdownregistry.com/api/v1/blob/e3cdfe5b1c5dcaa468baed69663e906df013bb4c72e0818e3c08b2be0a3ecf2f
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.