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 headline-craftgit 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/headline-craft)<a href="https://agentmods.dev/skills/shimo4228/claude-harness/headline-craft"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/headline-craft/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/headline-craft"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/headline-craft.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 | $0.00132 | $0.02383 |
| Opus 5 | $0.00066 | $0.01192 |
| Sonnet 5 | $0.00026 | $0.00477 |
| Haiku 4.5 | $0.00013 | $0.00238 |
Grade A, and why
headline-craft 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 3d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Headline Craft — 開かせる一行を作る
読者は本文を読む前にタイトルで開くかどうかを決める。このスキルは「何を書いてはいけないか」 (規範)でも「どれを採るか」(判定)でもなく、「どう候補を作るか」(生成)だけを担う。
役割分担(defer 宣言):
- 誠実さ規約・AI slop 禁止リスト →
writing-ecosystem(~/MyAI_Lab/zenn-content常駐)の Title Conventions が正本。本スキルの全候補はあのフィルタを通ってから提示する - platform 文字数・記法 → 各 project の publication channel contract。実値はここに書かない
- 公開記事候補の点検 →
title-revieweragent(~/MyAI_Lab/zenn-content常駐)。本 skill 自身の候補を自己採点しない - topics / emoji → platform を所有する project-local skill
実証知見(技法の根拠)
- ポジティブな飾り言葉は CTR を下げる: Upworthy の約 10.5 万 headline 変種の分析(Robertson et al. 2023, Nature Human Behaviour)で、ポジティブ語の追加は消費率を下げた。「素晴らしい」「強力な」系の形容は削るのが正しい。同研究はネガティブ語による CTR 上昇も示したが、恐怖・怒り駆動は Title Conventions が禁じる。
- 好奇心ギャップは情報の欠落: Loewenstein の information gap 理論。知っていることと知りたいことの差が開かせる。ただし本文が必ずギャップを埋めること — 埋めない好奇心ギャップがクリックベイトの定義
- 日本語圏の参考値: Qiita 全記事分析でバズ記事はタイトル 20–36 字に集中。各 platform の上限より短い方に最適帯がある
- トピック中心 → 結果駆動への進化: タイトルは戦いの 90%。詩的タイトル(意味不明で素通り)と教科書調(「〜の分析」= 宿題感)が二大失敗形。具体的数値・明示的な価値・人間の声の 3 点が指を止める(Kaguura 2026, 90 日で 20,585 購読者の実践知)
- タイトル A/B テストは読者関心の学習装置: Substack はタイトル A/B テストを機構として持つ。目的は釣りの最適化ではなく「読者が実際に何に関心があるか」を学ぶこと(明快な解決型 vs 興味深いパラドックス型、等)
技法カタログ
各技法に「適用条件」を付す。条件を満たさない技法は候補に使わない。
| 技法 | 型 | 適用条件 |
|---|---|---|
| 具体性 | 固有名詞・数値・状況を入れる(「LLM で」→「Claude Code の hooks で」) | 常時。迷ったらまずこれ |
| 結果駆動 | トピック名でなく読者が得る結果を言う(「Newsletter 成長モデルの分析」→「1,000 本を分析してわかった、登録が増える 3 つのレイアウト」) | 本文が実際にその結果を提供する |
| ベネフィット前置 | 読後に読者が得るものを先頭側に(「〜する方法」より「〜できるようになる」の中身を言う) | 本文が実際にそれを提供する |
| 誠実な好奇心ギャップ | 結論の手前まで言う(「試したら意外な結果になった」ではなく「試したら X だけが失敗した」) | 本文がギャップを完全に埋める |
| 対比・転換 | Before/After、期待と実際(「A だと思っていたが B だった」) | 実体験・実測が本文にある |
| 数字は証拠として | 実測値・件数を事実として使う(「32,487 件の A/B テストが示す〜」) | 数字が主役化しない(禁止の実値は writing-ecosystem Title Conventions) |
| 自分ごと化 | 読者の状況を主語に(「毎回忘れる人のための〜」) | ターゲット読者が実在し、本文がその人に応える |
| 問いの形 | why / how の知的関心(「なぜ X は Y になるのか」) | 本文が答えを出す。煽り疑問(「まだ X してるの?」)は禁止 |
削る技法(追加ではなく除去): ポジティブ形容詞(素晴らしい・強力な・完全な)、ヘッジ(〜について・〜の話・〜メモ)、冗長な前置き、em dash(——)による 2 文連結。削った字数を具体性に回す。
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.
- 3d ago Changed fa64139d379e
- 9d ago First seen · 78 lines · 132 tokens per session scan A a88d14791252
headline-craft is a skill published in the GitHub repository shimo4228/claude-harness (2 stars, last pushed 3d ago), licensed MIT. It adds 132 tokens to every session and 2,383 once invoked, about $0.0007 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 2026-08-31.
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.