cto-orchestration SKILL.md skillA

cto-orchestration from martin1847/evolab is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add martin1847/evolab/cto-orchestration@v1.8.0

Pins v1.8.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
martin1847/evolab
Path
skills/cto-orchestration/SKILL.md
Versions recorded
27
Latest version
v1.8.0, committed Nov 6, 2026
First version recorded
Sep 2, 2026
Size
16,160 bytes
Repository stars
7
License
MIT

以 CTO/orchestrator 模式管理多 agent 软件交付。用户要求“你做 CTO/编排者”“派 omp/codex 去做”“goal 模式派发”、管理多会话开发或接入这套工作流时使用;“复盘/收口/retro/retrospective”“工作盘点/盘点候选/stocktake”也必须触发,盘点只提案不动工。新项目先用 repo-governance-bootstrap 建治理骨架。不用于单 agent 小任务、无需评审循环的局部改动或纯文档初始化。.

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

# CTO Orchestration — 多 agent 软件交付

> 主干只留每次派工都要用的判据与路由;命令细节、故障矩阵和模板按需读 `references/`。
> **能电不文,电后即减**:能下沉 hook / gate 的规则不写散文;电上之后原正文收成一行指针(判据 `references/shock-in-the-loop.md` §1)——约束类散文的价值随门增多而递减,复盘 §3 同轮淘汰。

三条铁律:

1. **编排者不写产品代码**:只产出契约、调度、裁决和状态;实现与长 E2E 交给 worker(guard E1 + bash ⑳ 强制:编排位对源码/测试面的写入 → WARN 留痕,复盘按次数审;通道拼写与未覆盖面见 agentctl README §强制层)。
2. **不可逆先核事实与授权**:push / merge / 部署 / 删除 / 对外消息只认主理人真实新 turn;一次批准不外延。
3. **主理人持判断,不持状态**:可逆事项自驱,非紧急决策攒批;风险带证据、影响边界和下一步及时冒泡。

## 0. 角色与 lane

| 角色 | 责任 | 默认实现(可换) |
|---|---|---|
| 编排者 | 写 goal、派工、监控、裁决、落盘;不写产品代码;提示词 / 教义文本自己改(要派出则准最强模型),改完的测试再派 | 任意 shell + 文件 agent |
| 执行 agent | 按 goal 实现、自测、E2E、交付;不扩 scope;须可观测且可轮间 resume | omp / Claude Code |
| 评审 agent | 冷上下文只读挑刺,给 evidence + severity + verdict;不改码 | codex / 不同 lineage 模型 |
| 运维 agent | 对不可达环境只读取证与部署后验证;不顺手修复 | 用户转交只读取证提示词 |
| watcher | 返回 typed 状态;不把 idle 或沉默解释成完成 | `references/agentctl/` |

默认用 omp 执行、codex 评审,但**工具名不证明异构**;派工前看实际 model/backend,避免执行席与评审席落到同一 lineage 或 quota 池。

派工统一走 `agentctl start|steer|status|watch|stop`——**一条 lane、三引擎**各跑原生 duplex 协议,
能力差异不分叉车道(接口 typed 拒绝 + 指正路)。谁支持什么问 runtime(`agentctl capabilities`,状态词表 `agentctl states`),本文不留第二份能力表。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add martin1847/evolab/cto-orchestration@sha256:e2d585a778878d8b

The line at the top of this page pins the label v1.8.0, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_pjtlueeoqcp6m3pm.svg)](https://markdownregistry.com/a/art_pjtlueeoqcp6m3pm)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 27 versions of this file, between Sep 2, 2026 and Nov 6, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
v1.8.0 latest2026-11-06 66baa89 16,160 BA view · diff
v1.8.02026-11-06 332d1d9 15,876 BA view · diff
v1.8.02026-10-29 8b44fa3 15,804 BA view · diff
v1.7.122026-10-29 7345c25 15,805 BA view · diff
v1.7.122026-10-29 d3192ba 16,070 BA view · diff
v1.7.122026-09-30 974dee5 16,236 BA view · diff
v1.7.112026-09-30 fa36d18 16,236 BA view · diff
v1.7.112026-09-30 44d933a 16,284 BA view · diff
v1.7.112026-09-30 67e197b 16,092 BA view · diff
v1.7.112026-09-25 e710684 16,126 BA view · diff
v1.7.112026-09-23 042b1e1 16,033 BA view · diff
v1.7.112026-09-23 166b14a 15,959 BA view · diff
v1.7.112026-09-18 d97733f 15,707 BA view · diff
v1.7.102026-09-18 2840802 15,707 BA view · diff
v1.7.102026-09-18 ebfd02a 15,670 BA view · diff
v1.7.102026-09-17 2e98ca2 15,598 BA view · diff
v1.7.102026-09-13 af733ed 15,500 BA view · diff
v1.7.102026-09-13 ab00223 15,341 BA view · diff
v1.7.102026-09-11 5d69816 15,191 BA view · diff
v1.7.102026-09-10 a367ae9 15,153 BA view · diff
v1.7.92026-09-07 06ad47b 15,152 BA view · diff
v1.7.82026-09-06 f31eea8 15,152 BA view · diff
v1.7.82026-09-03 ca9b12f 15,053 BA view · diff
v1.7.72026-09-03 e8fa86a 15,053 BA view · diff
v1.7.72026-09-02 c0c6a21 15,032 BA view · diff
v1.7.72026-09-02 67fa670 14,979 BA view · diff
v1.7.72026-09-02 871e668 13,874 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (16160 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

GitHub

martin1847/evolab · 7 stars · license MIT · pushed 2026-11-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_pjtlueeoqcp6m3pm
GET https://markdownregistry.com/api/v1/resolve?ref=martin1847/evolab/cto-orchestration
GET https://markdownregistry.com/api/v1/blob/e2d585a778878d8bf991061fa4f291cfd79dbfb6bcaf4bdf18680a26f07bc61e

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.

More from martin1847/evolab

agent-backend-standard SKILL.md skill
martin1847/evolab · skills/agent-backend-standard/SKILL.md · 后端架构与工程规范。适用于构建或评审 agent/LLM 后端、任何涉及数据库(DB)的后端,以及建立或评审后端仓库工程门禁。
v1.4.3 · audit A · 7 stars
agent-frontend-standard SKILL.md skill
martin1847/evolab · skills/agent-frontend-standard/SKILL.md · 前端工程规范。适用于编写或评审前端/UI 代码(React、React Native/RN、Next.js、组件、样式、状态、测试)、建立前端工程门禁或将设计系统对接 AI。不用于仅从新用户视角探索产品卡点;该场景使用…
v1.0.1 · audit A · 7 stars
agent-mail SKILL.md skill
martin1847/evolab · skills/agent-mail/SKILL.md · 多编排者/长期 agent 身份之间的异步信箱总线——发信、收信、回信、归档、名册注册。每个身份一个 inbox,一封信只有一个去处(收件人 inbox),收信只查自己信箱。触发:给另一个编排者/CTO/agent…
v0.1.14 · audit A · 7 stars
frontend-explorer SKILL.md skill
martin1847/evolab · skills/frontend-explorer/SKILL.md · 探索型前端测试——派一个「第一次见这个产品」的探索者,用 playwright-cli 驱真浏览器走完一段旅程,回一份按挡路程度排序的「在哪卡住 / 哪里看不懂」清单,每条带屏幕原文与截图证据。触发:探索一遍 / 走一遍 / 踢踢轮胎 /…
v0.1.2 · audit A · 7 stars
git-workflow-standard SKILL.md skill
martin1847/evolab · skills/git-workflow-standard/SKILL.md · 生产级 Git 协作 SOP:受保护分支按仓库 tier 门禁、改动从 feature 分支起、集成默认 squash、rebase 判据、提交不加 AI 签名。任何 git commit / push / 开 PR / 建分支 /…
v1.2.0 · audit A · 7 stars
observability-standard SKILL.md skill
martin1847/evolab · skills/observability-standard/SKILL.md · 适用于编写或评审任何后端服务,包括普通服务与 agent/RAG 系统。覆盖日志、tracing、OpenTelemetry、上下文传播、日志级别、trace/log/DB 关联、边界类型及…
v1.3.3 · audit A · 7 stars
orchestrator-core SKILL.md skill
martin1847/evolab · skills/orchestrator-core/SKILL.md · 多智能体编排的领域无关内核。适用于抽象编排模式、创建新领域编排者,或设计多智能体架构。实际软件交付编排使用 cto-orchestration。不用于单 agent 一次性小任务或纯文档初始化。
v0.2.4 · audit A · 7 stars
repo-governance-bootstrap SKILL.md skill
martin1847/evolab · skills/repo-governance-bootstrap/SKILL.md · 一次性初始化 AI 协作项目的轻量工程治理骨架。新仓库 / 文档治理初始化时调用(也是 cto-orchestration 接入新项目的第一步)。One-shot governance bootstrap for a new repo.
v1.5.5 · audit A · 7 stars
source-coding-discipline SKILL.md skill
martin1847/evolab · skills/source-coding-discipline/SKILL.md · Use when a task involves reading, editing, reviewing, testing, debugging, refactoring, or otherwise working with source…
v0.1.2 · audit A · 7 stars

Every file in martin1847/evolab

Browse by kind, by grade A, or by owner.