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 CronusL-1141/AI-company --skill os-workflowgit clone --depth 1 https://github.com/CronusL-1141/AI-companyWrote 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/cronusl-1141/ai-company/os-workflow)<a href="https://agentmods.dev/skills/cronusl-1141/ai-company/os-workflow"><img src="https://agentmods.dev/badge/skills/cronusl-1141/ai-company/os-workflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cronusl-1141/ai-company/os-workflow"><img src="https://agentmods.dev/badge/skills/cronusl-1141/ai-company/os-workflow.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.02526 |
| Opus 5 | $0.00026 | $0.01263 |
| Sonnet 5 | $0.00010 | $0.00505 |
| Haiku 4.5 | $0.00005 | $0.00253 |
Grade A, and why
os-workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OS Workflow — 用 CC 工作流,但让产出回流 OS
背景
调用 Workflow 后,每个内部 agent 会被 hook 自动注册成一个 OS 团队(workflow-<wf_id>,
一次 workflow = 一个团队)。追踪是自动的,但工作内容不会自己入库——下面两件事必须你做。
1. 总任务上墙(Leader 职责,不变)
调用 Workflow 前/后,把这次工作方向用 task_create 登记到任务墙并置 running。
Leader 负责决策、设计、记录;执行交给 workflow——但账要记在 OS。
完成后 task_update 置 completed 并填 result。
2. 在每个 workflow agent 的 prompt 里嵌入「回写指令」
把下面这段粘进你写的 workflow 脚本里每个 agent() 的 prompt 末尾(已验证 workflow
agent 能调 OS 的 MCP 工具 + HTTP API,非沙盒):
【回写 OS(收尾必做)】
1. ToolSearch 加载:select:mcp__ai-team-os__task_memo_add,mcp__ai-team-os__report_save
2. 完成本职工作后:
- task_memo_add(task_id="<总任务id>", content="<这步干了啥+关键结论>", memo_type="progress")
- 重要产出再 report_save(...) 落库,并把 report_id 写进 memo
3. 你在项目目录运行,MCP 自动带项目头,无需关心端口/项目 id。
在脚本里把 <总任务id> 用第 1 步 task_create 拿到的 id 通过 prompt 字符串插值传进去。
脚本写法示例
// Leader 先 task_create 拿到 taskId(OS MCP),再写 workflow:
const WRITEBACK = `\n【回写 OS(收尾必做)】\n1. ToolSearch: select:mcp__ai-team-os__task_memo_add\n2. 完成后 task_memo_add(task_id="${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(用户裁定)
两档制:Fable = 编排层(统筹/架构裁决/终审),Opus = 执行层(一切 worker)。 不传 model 即继承主会话模型,所以在 Fable 会话里裸派会整场按 Fable 价率烧:
- 每个
agent()默认显式带model: 'opus'(层级别名,浮动到最新 Opus,不写死型号); - 仅终审/对抗裁决/最高难度修复的 stage 用
model: 'fable'(通常配effort: 'xhigh')。 - 每处
model: 'fable'调用须配一条// fable 理由: …行注释;Agent 工具派工则在 prompt 首行写[fable 理由: …]。S6 派工门禁(PreToolUse 机检):缺省 model 直接拦,fable 无理由拦。额度溢出时的放宽是临时特例,须缔造者当次明令并注明有效期,不得沉淀为常规。
// 典型分层:执行 stage 全 opus,终审 stage 才 fable
const found = await parallel(ITEMS.map(x => () =>
agent(findPrompt(x) + WRITEBACK, { model: 'opus', schema: FINDINGS })))
// fable 理由: 终审裁决需最强模型
const verdict = await agent(judgePrompt(found) + WRITEBACK,
{ model: 'fable', effort: 'xhigh', schema: VERDICT })
注:effort 由脚本作者按需自选,治理层不设档位制度;本纪律只软约束,无 hook 硬拦。
3.1 用量七规则(2026-09-05 缔造者裁定,方向记忆【模型分层与用量平衡】指向此处)
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 Changed · +30 lines f99102df2178
- 11d ago First seen · 81 lines · 51 tokens per session scan A 480735273445
os-workflow is a skill published in the GitHub repository CronusL-1141/AI-company (357 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 2,526 once invoked, about $0.0003 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
任务链可视化
A guide and script for turning task files and project documents into one self-contained HTML page. The page shows task status, dependencies, and how acceptance criteria (ACs) link back to tasks.
task
AI DevKit · Track dev-lifecycle / structured-debug progress on a durable task with the ai-devkit task CLI. Use to record phase, progress, next step, blockers, and validation evidence.
flowai-team-dashboard
A team-management dashboard layout with tabs for members, team details, and activity logs, plus charts and data export.
kanban-board
A Kanban board is a visual task list with columns for stages such as To do, In progress, In review, and Done. It can show filters, labels, due dates, assignees, comments, and swimlanes that group cards.
project-manager
Project management expert for Agile, estimation, risk management, and stakeholder communication.
agentlas-operations
A set of operating procedures for running Agentlas, a system for coordinating agents, reusable workforces, automation graphs, and shared agent resources. It covers candidate selection, graph creation, asset discovery, and memory rules.