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 devcxl/mattpocock-skills-zh --skill writing-fragmentsgit clone --depth 1 https://github.com/devcxl/mattpocock-skills-zhWrote 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/devcxl/mattpocock-skills-zh/writing-fragments)<a href="https://agentmods.dev/skills/devcxl/mattpocock-skills-zh/writing-fragments"><img src="https://agentmods.dev/badge/skills/devcxl/mattpocock-skills-zh/writing-fragments/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/devcxl/mattpocock-skills-zh/writing-fragments"><img src="https://agentmods.dev/badge/skills/devcxl/mattpocock-skills-zh/writing-fragments.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 | $0.00021 | $0.00921 |
| Opus 5 | $0.00010 | $0.00461 |
| Sonnet 5 | $0.00004 | $0.00184 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
writing-fragments 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.
What it actually says
这是纯粹的 explore（探索）：拓宽可被写作的空间，不承诺任何结构：承诺结构是 exploit（利用） 的任务，由另一个技能负责。进行一次产生碎片的盘问，就用户想写的任何话题不断追问。强加阶段、大纲或文章结构在此不在范围内。
当对话双方的碎片浮现时，将它们追加到一份 markdown 文件中。
如果用户没有传入保存路径，询问一次文档保存到哪里，然后在整个对话中记住它。
从用户说的第一件事（包括初始 prompt）开始就捕捉碎片。
首次写入时，在顶部放一个 H1 的工作标题（以后可以改），除此之外什么都不放：没有元数据、没有目录、没有日期。
什么是碎片
碎片是任何可能在最终文章中幸存下来的文本片段。它必须对作者具有可读性：作者能理解它的意思：但它不需要定义其术语，也不需要对陌生读者来说可以理解。标准是"这是一段好的写作吗？"，而不是"这是一个完整的论证吗？"
碎片刻意保持异质化。哪些可以成为碎片的例子：
- 一个你想用但还不知道放在哪里的犀利句子。
- 一个带有一句话论证的主张。
- 一个小插曲：一件发生过的事、一段代码片段、一个场景、一个类比。
- 一个半成品想法："某件事感觉像某件事，以后再展开。"
- 一句引用、一段对话、一句无意中听到的话。
- 一组凭感觉聚在一起的观察。
- 一个抱怨、一个坦白、一个笑点。
- 一个引导词（leading word）：一个紧凑的隐喻或新造词，整个文章可以挂靠其上（用一个词来命名这个想法，就像 tracer bullets（曳光弹） 或 fog of war（战争迷雾） 命名了一个完整模式）。
其中，引导词是最有价值的碎片。它是承重结构：在探索阶段找到恰如其分的词，就能塑造整个文章的结构、过渡和标题：在整个利用阶段持续受益。当对话反复围绕某个想法时，推动为它造一个词。
小说家的日记是这里的模式：多年来无结构的觉察，后来被开采为原始素材。碎片就是觉察。
文件格式
# 工作标题
第一个碎片放在这里。
它可以有多段。可以包含列表、代码、引用：碎片自然是什么形状就
写成什么形状。
---
第二个碎片。
---
> 用户想保留的一句引用。
对它的回应。
---
- 一组相关的观察
- 凭感觉聚在一起
- 想彼此靠近放置
碎片之间用水平分隔线（\n---\n）分隔。正文中没有标题。没有标签。没有超出添加顺序以外的排序。
写作节奏
静默追加。不要为每个碎片请求许可。顺带提一下你添加了什么（"加上这个"），但不要用保存弹窗打断对话。
每次写入前：从磁盘重新读取文件。用户可能在两轮对话之间编辑、重新排序或删除了碎片：保留他们的修改。永远不要覆盖文件；只追加（或者，如果用户要求，就地编辑某个特定碎片）。
用户可以随时说"删掉最后一个"、"把那个重写得更有力一点"、"把那两个合并"。将这些视为一等指令来对待。
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.
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.
- 12d ago First seen · 80 lines · 21 tokens per session scan A b18e6232da93
writing-fragments is a skill published in the GitHub repository devcxl/mattpocock-skills-zh (343 stars, last pushed 7d ago), licensed MIT. It adds 21 tokens to every session and 921 once invoked, about $0.0001 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
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
chinese-code-review
A Chinese-language code-review communication guide with templates and severity levels for review comments.
chinese-commit-conventions
A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
dispatching-parallel-agents
A workflow for assigning separate coding agents to independent tasks that do not share state or depend on one another. Each agent receives a focused scope, constraints, and an expected result.
executing-plans
A procedure for carrying out a written software implementation plan in a separate session, including reviewing the plan, completing its tasks, and checking the results at defined review points.