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 shimo4228/claude-harness --skill llms-txt-writergit clone --depth 1 https://github.com/shimo4228/claude-harnessWrote 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/shimo4228/claude-harness/llms-txt-writer)<a href="https://agentmods.dev/skills/shimo4228/claude-harness/llms-txt-writer"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/llms-txt-writer/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/shimo4228/claude-harness/llms-txt-writer"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/llms-txt-writer.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 | $0.00113 | $0.03995 |
| Opus 5 | $0.00056 | $0.01997 |
| Sonnet 5 | $0.00023 | $0.00799 |
| Haiku 4.5 | $0.00011 | $0.00400 |
Grade A, and why
llms-txt-writer 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 4d 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.
This is a copy
97% identical to llms-txt-writer — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
llms-txt-writer — AI-Facing Writing Skill
AI 検索エンジン（ChatGPT / Perplexity / Gemini）と AI エージェントに引用・参照されることを最適化した文書を書くスキル。静的解析（GEO-SFE）と Answer.AI llms.txt 標準の両方をカバーする。
When to Use
以下のいずれかに該当するとき:
llms.txt/llms-full.txtを新規作成・更新する- FAQ / 用語集など AI 検索引用を狙うドキュメントを書く
- 既存の AI-facing 文書の GEO スコアを診断・改善する
使わない場面:
- README / repo のトップページ（
readme-writerを使う — 証拠スクリプト + fresh context の判定器 + review panel を持つ） - 記事 / エッセイ / ブログポスト等の人間向けコンテンツ（
writing-ecosystemを使う） - 人間可読性を最優先したいドキュメント
Audience Separation: Human vs AI
ドキュメントは 人間 primary か AI primary かで最適化が根本的に異なる。1 ファイルで両立させると、どちらにも中途半端になる。
| 軸 | 人間 primary | AI primary |
|---|---|---|
| 構造 | 物語的、段落で流れる | Q&A / 定義形式、H2 独立 chunk |
| 見出し | 宣言形で簡潔 | 質問形で 20%+ |
| エンティティ配置 | 文脈に合わせて自然に | 冒頭 30% に 45%+ 集中（ski-ramp） |
| 定義 | 文脈から読み取れる | X is defined as Y を明示 |
| セクション長 | 論点重要度に比例 | 50-150 語 / 150-450 字に揃える |
| 読みやすさ | 最優先 | 犠牲にしてよい |
本 skill は AI primary の最適化のみ扱う。
Answer.AI llms.txt Standard（v2 — as-of 2026-08-23 に一次ソース確認）
llmstxt.org（Jeremy Howard / Answer.AI。2024-09-03 公開、v2 は 2026-08-10 更新）。
spec が定めるのは llms.txt だけ:
- 必須は H1（プロジェクト名）のみ。順序は BOM（任意）→ H1 → 要約 blockquote → 見出し以外の詳細 markdown → H2 区切りのファイルリスト
Optionalセクション = 二次情報。「より短い context が要るときエージェントが スキップしてよいリンク」という意味（機械的な必須/任意の区別ではない）- 発見用の link relation（HTTP
Linkヘッダまたは HTML<link>で提供する）:rel="describedby"→ llms.txt 本体、rel="alternate" type="text/markdown"→ markdown 版ページ .mdURL 規約:page.html.md（付加）/page.md（置換）/ ルートはindex.html.mdまたはindex.md- サブパスの llms.txt: 「A file covers the URLs under its path」。複数該当するときは 最も具体的なものを使う
llms-full.txt は spec に無い（llms_txt2ctx の context expansion も v2 の本文に記載なし）。
以下の 2 ファイル構成はコミュニティ慣行として本 skill が採る運用であって、標準準拠ではない:
| ファイル | 役割 | 内容 | サイズ目安 |
|---|---|---|---|
llms.txt |
Navigator（spec 準拠） | H1 + 要約 blockquote + H2 カテゴリ + bullet リンク列 | ~5 KB |
llms-full.txt |
自己完結型コンテンツ（spec 外の慣行） | FAQ + 用語集 + 引用参照などの full content | ~20 KB |
What ships with it
9 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.
- 4d ago Changed 9dd07e0c749a
- 11d ago First seen · 284 lines · 113 tokens per session scan A 7e3bac934eee
llms-txt-writer is a skill published in the GitHub repository shimo4228/claude-harness (3 stars, last pushed 5d ago), licensed MIT. It adds 113 tokens to every session and 3,995 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to llms-txt-writer, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
agent-adoption-triage
Five-question triage for routing AI work to the right architecture — script, algorithmic search, LLM workflow, or autonomous agentic loop — before any agent is built. Use when someone says "let's build an agent for X", when deciding whether a use case actually needs an autonomous agent, when reviewing an agent…
job-description-skill
A job-description analysis skill that turns a vacancy listing and a candidate’s background into an HTML report about fit, gaps, interview topics, and application strategy.
offer-compare-skill
A decision assistant for comparing two or more job offers across pay, growth, company strength, team risk, promotion, AI exposure, and lifestyle. Total compensation means the combined value of salary, bonuses, shares, and sign-on payments.
offer-toolkit-skill
A set of job-search tools covering the path from finding a vacancy to accepting an offer. It includes separate tools for job searches, job-description analysis, tailored resumes, behavioral interviews, offer comparisons, and salary negotiation.
bq-skill
A coaching workflow for building a reusable library of truthful stories for behavioral job interviews. It uses structures such as STAR—Situation, Task, Action, Result—and can connect stories to a job description and résumé.
linkedin-job-search-skill
A job-search assistant that uses a sample job description and your resume to find and rank similar public LinkedIn Jobs listings. LinkedIn Jobs is LinkedIn’s section for advertised employment positions.