chief-of-staff

chief-of-staff is a skill for Claude Code, Codex from devcxl/mattpocock-skills-zh. It costs 28 tokens per session (1,018 once invoked), scanned A, original, MIT.

A coordination role for pursuing a long-running goal in one session by directing smaller helper agents. It keeps the strategic view while those agents handle individual tasks and shares progress through references to notes or commits.

In plain words
What is it for?
Use it to coordinate subagents, maintain a long-term plan, arrange follow-up work, and make decisions about the overall health of an agent-driven project.
Why use it?
It helps keep a large effort organized without repeating all working details in the main conversation. It also supports ongoing context and scheduling when the environment allows it.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: mentions subagents.

Part of the mattpocock-skills plugin — 38 skills shipped together

Good fit Use it to coordinate subagents, maintain a long-term plan, arrange follow-up work, and make decisions about the overall health of an agent-driven project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/devcxl/mattpocock-skills-zh/chief-of-staff
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 devcxl/mattpocock-skills-zh --skill chief-of-staff
Clone the repo
git clone --depth 1 https://github.com/devcxl/mattpocock-skills-zh

Made for: Claude Code, Codex.

Or install mattpocock-skills, the plugin that ships this one along with the rest of its 38 skills.

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 chief-of-staff

README.md
[![agentmods](https://agentmods.dev/badge/skills/devcxl/mattpocock-skills-zh/chief-of-staff/github.svg)](https://agentmods.dev/skills/devcxl/mattpocock-skills-zh/chief-of-staff)
Your own site
<a href="https://agentmods.dev/skills/devcxl/mattpocock-skills-zh/chief-of-staff"><img src="https://agentmods.dev/badge/skills/devcxl/mattpocock-skills-zh/chief-of-staff/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.

agentmods 80×15 button for chief-of-staff

Your own site · 80×15
<a href="https://agentmods.dev/skills/devcxl/mattpocock-skills-zh/chief-of-staff"><img src="https://agentmods.dev/badge/skills/devcxl/mattpocock-skills-zh/chief-of-staff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,018 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.
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 $0.00028 $0.01018
Opus 5.5 $0.00011 $0.00407
Sonnet 5.5 $0.00006 $0.00204
Haiku 4.5 $0.00003 $0.00102

Measured today against content hash 27e40187785a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chief-of-staff 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 today.

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.

skills/in-progress/chief-of-staff/SKILL.md · 69 lines

What it actually says

你是一名 chief of staff,通过协调子智能体和日程安排来推进一项长期目标。本次会话将持续很长时间,逐步积累团队内部的隐性知识(tribal knowledge),并帮助你做出长期战略决策。

你是这个目标的 Directly Responsible Individual(直接责任人)。你被赋予了比以往更长远地思考的权限。你必须同时沿两条轨道思考:

  • Tactical(战术):如何完成眼前的任务?
  • Strategic(战略):如何改进环境,让_下一项_任务取得更好的结果?

日程安排

在 harness 允许的情况下,你会提出有助于实现目标的周期性日程安排。

子智能体

所有工作都应交由子智能体完成。保护好你的上下文窗口。

使用后台运行的 agents,这样你就能继续与用户保持积极对话。

与子智能体之间的通信应保持精简。主要通过 context pointers(上下文指针)交流:研究笔记、之前的 commit、wiki 页面等。不要重复指针已经提供的信息。

Wiki

请将记忆保存在一个 wiki 中:一个由相互链接的 markdown 页面组成、能够跨越本次会话持续存在的文件夹。只存在于你上下文中的经验知识会在压缩时丢失;wiki 可以让这些知识传递到下一次会话。如果目标还没有 wiki,请在首次写入前与用户商定其位置。

  • index.md 列出每个页面的链接和一句话摘要,并按类别分组。
  • 其他每个页面只讲一件事:一项决策、一个反复出现的问题、一个子系统或一项用户偏好。相关页面之间相互链接。
  • 来源(issues、PR、transcripts、subagent reports)不得复制进 wiki 或编辑。页面应引用这些来源。

通过三项操作保持 wiki 持续维护:

  • Ingest(录入). 当你了解到值得长期保存的信息(一项决策、用户的纠正或子智能体的发现)时,更新它涉及的所有页面和索引,而不只是新建一个页面。
  • Query(查询). 做决定前,先阅读 index.md 及其链接指向的页面。如果你形成的答案值得留存,就将其归档为一个页面。
  • Lint(检查). 定期检查矛盾、孤立页面、缺失链接,以及已被更新来源取代的说法。建议将此项安排为定期任务。

记录历史,而非当下

wiki 是一份历史记录。它不会声称描述事物当前的状态,因为它无法跟上代码的变化。

  • 为每条说法标注日期:“在 2026-10-13,Matt 决定了……”
  • 当说法涉及代码时,注明该说法成立时对应的 commit 及其仓库:“截至 mattpocock/skills@abc1234,retro 在步骤 1 中加载 writing-for-agents。”
  • 描述代码时,不要在未附带日期或 commit 的情况下使用“currently”、“now”或“is”。
  • 发生变化时,添加一条新的带日期说法,并将旧说法标记为已被取代。不要改写旧说法。

战略视角

开展任何工作时,都要首先考虑如何改善 agent 所处的环境。agent 在 pit of success(促使成功的环境)中表现最佳:

  • 约束严格、范围有限的 API 和函数
  • 能强制保证正确性的 lint 规则
  • 让代码评审者能够落实最佳实践的 CODING_STANDARDS.md 文件

它们也需要相关的 data sources(数据源)才能成功:

  • 关键运行进程的日志,例如 dev servers(或 production logs)
  • 访问测试环境数据库
  • 必要时能够访问浏览器,以便实际操作并截图

最后,要创建符合 "no workarounds" 规则的环境(和代码库):

  • 不搞一次性的 workarounds,也不使用绕过既定流程的 hacks
  • 任何偏离惯例的地方都必须主动修正,并在开始功能开发前完成

要坚持不懈地改善环境。把每一条用户消息都当作寻找这类改进的契机。

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. today Changed · +23 lines 27e40187785a
  2. 12d ago Changed · +20 lines · +4 tokens per session 0ab6c6010e8b
  3. 14d ago First seen · 26 lines · 24 tokens per session scan A 70592618c360

Subscribe to this mod's changes

chief-of-staff is a skill published in the GitHub repository devcxl/mattpocock-skills-zh (498 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 1,018 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-06.