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 shousper/claude-kit --skill writing-docsgit clone --depth 1 https://github.com/shousper/claude-kitWrote 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/shousper/claude-kit/writing-docs)<a href="https://agentmods.dev/skills/shousper/claude-kit/writing-docs"><img src="https://agentmods.dev/badge/skills/shousper/claude-kit/writing-docs/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/shousper/claude-kit/writing-docs"><img src="https://agentmods.dev/badge/skills/shousper/claude-kit/writing-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00078 | $0.01544 |
| Opus 5.5 | $0.00031 | $0.00618 |
| Sonnet 5.5 | $0.00016 | $0.00309 |
| Haiku 4.5 | $0.00008 | $0.00154 |
Grade A, and why
writing-docs 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 1mo 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing documentation
Overview
This skill covers the structure of documentation: what a page is for, how it is organized, and how its parts are formatted. The voice and word choice rules already apply to everything you write; this skill adds the structural conventions of the Google developer documentation style guide, condensed and adapted for code repositories.
When to use
Use it when you create or change a documentation file (Markdown, RST, AsciiDoc, HTML), a README, a design document or ADR, a changelog entry, a docstring, or a comment block that explains a module, type, or function.
Do not use it for commit messages, pull request descriptions, chat replies, or inline comments of a line or two. Those follow the writing style on their own. Do not use it for the code itself; formatting of docstrings and comments follows the language's conventions, and this skill governs only the prose inside them.
Before you write
Name the reader and pick one purpose for the page: explain a concept, complete a task, look something up, or learn by doing. A page that mixes purposes is harder to use than two short pages. Be prescriptive: recommend one path and mention alternatives only when the reader needs them to decide.
Core rules
Headings: sentence case; task headings are bare infinitives ("Create an instance"), concept headings are noun phrases ("Instance lifecycle"); no -ing openers, no numbering, no code, no links, no trailing punctuation; one H1 per page; never skip a level; never leave a heading without content.
Paragraphs: one idea each, one to four sentences, key point first. Break long paragraphs rather than lengthening sentences.
Lists: introduce a list with a complete sentence ending in a colon; use a numbered list only for a sequence; use a bulleted list for three or more parallel items; capitalize each item; end items that are sentences with a period; use term-and-description pairs with colons, never dashes; never make a list of one item.
Procedures: one action per step; state the goal or location before the action ("In the Settings page, select Billing"); prefix optional steps with "Optional:"; write a single-step procedure as one bullet; put results after the action, in the same step.
What ships with it
5 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.
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.
- 1mo ago First seen · 97 lines · 78 tokens per session scan A 261f6133e5c0
writing-docs is a skill published in the GitHub repository shousper/claude-kit (4 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 1,544 once invoked, about $0.0003 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 2026-09-06.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…