writing-for-agents

writing-for-agents is a skill for Claude Code, Codex from devcxl/mattpocock-skills-zh. It costs 33 tokens per session (3,287 once invoked), scanned A, original, MIT.

A Chinese-language writing guide for documents that coding agents read, including skills and AGENTS.md or CLAUDE.md files.

In plain words
What is it for?
Use it when creating or editing agent instructions, skills, or project guidance files.
Why use it?
It helps make instructions predictable by clarifying when supporting documents should be consulted and separating required steps from reference material.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the mattpocock-skills plugin — 37 skills shipped together

Good fit Use it when creating or editing agent instructions, skills, or project guidance files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/devcxl/mattpocock-skills-zh/writing-for-agents
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 writing-for-agents
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 37 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 writing-for-agents

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/devcxl/mattpocock-skills-zh/writing-for-agents"><img src="https://agentmods.dev/badge/skills/devcxl/mattpocock-skills-zh/writing-for-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,287 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 $0.00033 $0.03287
Opus 5 $0.00016 $0.01643
Sonnet 5 $0.00007 $0.00657
Haiku 4.5 $0.00003 $0.00329

Measured 12d ago against content hash 73c03750b0a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

writing-for-agents 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 12d 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.

skills/productivity/writing-for-agents/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

一份用于编写智能体所阅读的任何文档的参考:一个技能、一份 AGENTS.md / CLAUDE.md、一份通过指针触达的文档。包装方式各异,但写作规则是一致的:同样的杠杆让每份文档都变得可预测,因为智能体每次运行采取的是同一个流程,而不是产出同一个输出。

当你正在编写的文档是一个技能时,请阅读 SKILL-MECHANICS.md,了解前置元数据、调用方式的选择,以及路由技能。

上下文指针

上下文指针(context pointer) 是智能体上下文中持有的一条引用,它指向一份"上下文之外"的资料,并编码了触达该资料的条件。技能的 description 就是一条;AGENTS.md 中指向某份文档的一行也是同一回事。决定智能体何时、以多高的可靠性触达这份资料的,是这条指针的措辞,不是它的指向。一个本应被触达的指向目标,却藏在一段措辞含糊的指针背后:这是一个方差 bug:先打磨措辞;只有当打磨失败时,才把资料直接内联进去。

一条指针承担两件事:说明这份资料是什么,以及列出应当触发触达它的分支(branch 是这份文档所处理的一种独立情形,所以不同次运行会走不同的路径)。每一条始终加载的指针里的每一个词,在每一次轮次中都在付代价,所以它需要比正文更严格的精简:

  • 把"引导词"前移:指针是触发工作真正发生的地方。
  • 一个分支对应一个触发词。 同义词把同一个分支换了个说法写两遍,本质上是一个分支;把它们合并,只保留真正不同的分支。
  • 去掉正文已经承载的身份信息。

两种负载

你新增的每一份文档与每一条指针,都在花两种预算之一:

  • 上下文负载(Context load):始终加载的资料占据智能体窗口的代价:一行 AGENTS.md、一条技能描述,任何始终留在上下文里、无论是否触发都在消耗 token 与注意力的东西。
  • 认知负载(Cognitive load):消耗在人类身上的代价:有哪些文档存在、各自在什么时候用。人类就是这个索引。它不是要被最小化的代价:它是人类能动性的价格;把它花在需要人类判断的地方,在不需要的地方去除。

只通过指针触达的资料,逃脱了上下文负载,代价是这条指针自身那一行;完全没有指针的资料,则完全依靠认知负载。

信息层次

一份文档由两种内容类型组成:步骤(steps)(智能体按顺序执行的动作)和参考资料(reference)(按需查阅的定义、规则、事实)。两者可以自由混合:全是步骤(一份操作指南)、全是参考资料(一份审查规则,就像本技能)、或者两者兼具。核心决策是:每块内容应该放在信息层次的哪一级:这是一架按"智能体对资料的即时需要程度"排序的梯子:

  1. 文件内步骤(In-file step) 是主要层级:智能体按顺序做的事情。
  2. 文件内参考资料(In-file reference) 按需查阅。常常是合理的扁平同级集合(一条审查规则就是一个层级),这是妥当的安排,不算坏味道。
  3. 披露型参考资料(Disclosed reference) 被推到一份独立的文件中,通过一条上下文指针触达,仅在该指针触发时才加载。跨度可以是从同一文件夹里的相邻文件,到放在任何地方的完全外部参考资料:任何文档都可以指向它。

向下推得不够,顶层就会臃肿;向下推得太多,就会把智能体真正需要的资料藏起来。这种张力就是整个决策。

渐进披露(Progressive disclosure) 是沿着这架梯子向下移动(移出主文件、藏到指针背后)的过程,目的是让顶层保持清晰可读。它主要不是为了优化 token:它是保护这架层次结构的手段。分支是最干脆的披露测试:每个分支都需要的内容内联,只有部分分支才会触达的内容推到指针背后。当一份文档有步骤时,本应被披露的文件内参考资料会把它们埋掉,让关注它们变成一件靠运气的事:这是一个方差杠杆,不只是一个可读性杠杆。

共置(Co-location) 是文件内的同伴概念:层次结构决定一块内容要放得多深,共置决定一旦放到那里,什么内容与它并排。把一个概念的定义、规则、注意事项放在同一个标题下,而不是散布在各处,这样读到一处时,它旁边的内容也会跟着进入视野。检验标准是:这份文档读起来,应该像为智能体写的文档。归在一处的资料读起来是这样;分散的资料则不是。(这与"重复"是不同的概念:重复是把同一个意思说两遍;分散是把一个意思碎成多块。)

蔓延(Sprawl) 是这里的失败模式:一份文档即使每行都是活的、独特的,也只是单纯地太长。注意力会在冗余中变薄,每多出一行就多一分维护相关性的负担。治疗手段就是这架梯子:通过指针披露参考资料,并按分支或顺序拆分,让每条路径只携带它需要的内容。

Read the full file on GitHub · 82 lines

Files

What ships with it

2 files 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. 12d ago First seen · 82 lines · 33 tokens per session scan A 73c03750b0a3

Subscribe to this mod's changes

writing-for-agents is a skill published in the GitHub repository devcxl/mattpocock-skills-zh (340 stars, last pushed 6d ago), licensed MIT. It adds 33 tokens to every session and 3,287 once invoked, about $0.0002 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.