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 prose-translationgit 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/prose-translation)<a href="https://agentmods.dev/skills/shimo4228/claude-harness/prose-translation"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/prose-translation/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/prose-translation"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/prose-translation.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 | $0.00174 | $0.03096 |
| Opus 5 | $0.00087 | $0.01548 |
| Sonnet 5 | $0.00035 | $0.00619 |
| Haiku 4.5 | $0.00017 | $0.00310 |
Grade A, and why
prose-translation 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 5d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prose-translation — 日本語⇄英語 voice 保持翻訳（両方向）
人間向け prose を、著者の声と出力先channelのregisterを保ったまま自然に訳すためのスキル。
voice 非収束な prose の翻訳本体は、メインループ（最上位モデル）が本方法論に従って実行する。 サブエージェントへの handoff は会話文脈と voice 制約を落とす。
定型 pipeline の venue 翻訳はこの限りではない。用語集・タグ規約を使う宛先稿の準備は project agent が担ってよい。その場合も訳出の方法論は本 skill が正本で、agent は起動時に 本 skill を先に読む。agent は準備で停止し、投稿は宛先稿自身のgate / 著者GO後にproject publisherが行う。
Scope
- 対象: JA→EN と EN→JA の両方向。essay / opinion / research doc / README / ADR / glossary 等、人間向け prose。 共通骨格（絶対ルール・5 ステップ・QA・Review）は方向に依らず同じで、方向固有の判断だけを 下の「EN→JA 方向の追加規約」が持つ。
- 対象外:
- AI 向け doc（
llms.txt/llms-full.txt/ FAQ）→llms-txt-writer - 学術 citation / reference list の format 検証 →
citation-formatter
- AI 向け doc（
- defer: AI-slop原則・Title規約・出典編入は
writing-ecosystem、言語別slop診断は同skillのreferences/style-diagnostics.mdを正本とする。 - defer: 出力先channelのvoice / register / 語尾の実値は、そのprojectのpublication channel contractを正本として引く。
絶対ルール（そのまま保持するもの）
- コードブロック（```）・インラインコード（
backtick）は翻訳しない - Markdown 構文（#, -, |, [], ![]）・画像パス・URL・DOI はそのまま保持
- frontmatter は title のみ訳す（他はそのまま）
- term-lock 表の
never_translate項目はそのまま
Methodology — 5 ステップ
1. Pre-pass: term-lock と voice fingerprint
翻訳前に2つの表を作る。
term-lock（訳語を固定する語）:
| 種別 | 例 | 方針 |
|---|---|---|
| 造語・術語 | minimum disclosure set / moral crumple zone | 既存の英語術語があればそれを使う。著者造語は初出で定義 |
| 固有名詞 | 水俣病 → Minamata disease | 定訳。初出に短い gloss |
| 日本固有語 | 三権分立 / チッソ | 英語読者に通じる訳 + 必要なら短い gloss |
voice fingerprint（著者の声を英語に写す指標）:
- register: 原文の語尾を機械転写せず、出力先のpublication channel contractを引く。
- stance: 原文とtarget contractが発見調なら推論・修辞疑問を保持し、実用の直接指示ならhedgeへ弱めない。
- 文長リズム: 短い断定文の連打は英語でも短文で写す
- 修辞疑問: 原文の問いは英語でも問いで残す（結論を叩きつけない）
- 未解決の正直さ: 「まだわからない」は smooth に解決させず正直に訳す
2. Pass 1 — 意味 + voice 訳
逐語でなく、出力言語として自然にする。段落・見出し構造、原文の確度、target contractのvoiceを保つ。 日本固有参照はinline glossか軽い訳注を添える。
3. Pass 2 — self-edit
writing-ecosystemのAI-slop原則と、兆候がある場合のstyle diagnosticsで自己添削する。target contractの direct / discoveryその他のvoiceを保ち、日本語の謙遜・婉曲表現は英語圏の該当channel慣習に合わせる。
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.
- 5d ago Changed cd3cb8eb2bc5
- 10d ago First seen · 166 lines · 174 tokens per session scan A 72e971a6e765
prose-translation is a skill published in the GitHub repository shimo4228/claude-harness (3 stars, last pushed 4d ago), licensed MIT. It adds 174 tokens to every session and 3,096 once invoked, about $0.0009 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
write-terva-locale
Translate the terva interface into another language, complete or fix a locale, or wrap new strings for translation. Use when the user asks to localize terva or to add or finish a language (fi, pt-BR, ...). Also use to edit translated text or to contribute a translation upstream.
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…
localize
Full localization pipeline: scan for hardcoded strings, extract and manage string tables, validate translations, generate translator briefings, run cultural/sensitivity review, manage VO localization, test RTL/platform requirements, enforce string freeze, and report coverage.
deutsch-englisch-digitale-inhalte-handbuch
Für Deutsch Englisch AGB: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Schnittstellenkarte mit Zuständigkeits- und Nachweisfragen. Fachgebiet: AGB-Recht-Prüfer. Route: deutsch-englisch-digitale-inhalte-handbuch.
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.