hashiiiii-write-ja

hashiiiii-write-ja is a skill for Claude Code from hashiiiii/rules-for-ai. It costs 26 tokens per session (920 once invoked), scanned A, original, MIT.

A writing guide for creating, editing, and reviewing Japanese prose. It covers clear structure, accurate wording, consistent terms, and preserving facts and conditions.

In plain words
What is it for?
Use it for Japanese documentation, messages, articles, drafts, and editing or review requests.
Why use it?
It helps prevent accidental changes to meaning, unsupported claims, unclear sentences, and inconsistent Japanese style.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the rules-for-ai plugin — 7 skills, 2 hooks shipped together

Good fit Use it for Japanese documentation, messages, articles, drafts, and editing or review requests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hashiiiii/rules-for-ai/hashiiiii-write-ja
Install

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.

Any agent
npx skills add hashiiiii/rules-for-ai --skill hashiiiii-write-ja
Clone the repo
git clone --depth 1 https://github.com/hashiiiii/rules-for-ai

Made for: Claude Code.

Or install rules-for-ai, the plugin that ships this one along with the rest of its 7 skills, 2 hooks.

Wrote 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.

agentmods badge for hashiiiii-write-ja

README.md
[![agentmods](https://agentmods.dev/badge/skills/hashiiiii/rules-for-ai/hashiiiii-write-ja/github.svg)](https://agentmods.dev/skills/hashiiiii/rules-for-ai/hashiiiii-write-ja)
Your own site
<a href="https://agentmods.dev/skills/hashiiiii/rules-for-ai/hashiiiii-write-ja"><img src="https://agentmods.dev/badge/skills/hashiiiii/rules-for-ai/hashiiiii-write-ja/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.

agentmods 80×15 button for hashiiiii-write-ja

Your own site · 80×15
<a href="https://agentmods.dev/skills/hashiiiii/rules-for-ai/hashiiiii-write-ja"><img src="https://agentmods.dev/badge/skills/hashiiiii/rules-for-ai/hashiiiii-write-ja.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 920 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00920
Opus 5 $0.00013 $0.00460
Sonnet 5 $0.00005 $0.00184
Haiku 4.5 $0.00003 $0.00092

Measured 3d ago against content hash 4be071ffd4a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

hashiiiii-write-ja 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.

skills/hashiiiii-write-ja/SKILL.md · 47 lines

What it actually says

日本語の文章

分かりやすい下書きを作り、言葉と構成を推敲する。 読み手、文体、形式、長さは依頼に合わせる。

意味

  • 事実、数量、条件、例外、不確実さ、義務と推奨の違いを保つ。一部の観察を全体の話に広げない。
  • 原因、出典、意見、体験を作らない。
  • URL とコード、コマンド、識別子、パス、引用、製品名は、変更が依頼に含まれない限り、そのまま残す。
  • 同じ意味には同じ語を使う。異なる概念を一つの語にまとめない。

下書き

  • 読み手が必要とする要点から書く。一文に一つの主な内容、一段落に一つの話題を置く。
  • 身近な語と素直な動詞を使う。専門語は、読み手に説明が必要なときだけ補足する。
  • 主語と述語を対応させ、修飾語を係り先に近づける。長い修飾や二重否定は、意味を保って言い直す。
  • 主体が分かる場合は明示する。システムの動作もそのまま書く。主語を埋めるために人を作らない。
  • 手順は一文につき一つの操作にする。前提条件は、操作を始める前に分かる位置に置く。
  • 敬体と常体は依頼や原文に合わせる。文末に変化をつけるために混ぜない。

推敲

  • 内容を予告するだけの前置きや、中身のない強調を削る。例えば、「本質的な価値」「シームレスな体験」「特筆すべきは」。
  • 抽象的な評価を、与えられた具体的な事実に戻す。残す事実がなければ、その評価を削る。
  • 要点を直接書く。飾りの対比、問いかけ、結論の繰り返し、引用以外の不要な括弧やダッシュを削る。
  • 判断に必要な比較、留保、礼儀は残す。人間らしさのために感情や伝聞を足さない。
  • 見出しや箇条書きは、探しやすさや比較に役立つときに使う。項目を無理に 3 つにしたり、段落を同じ長さにそろえたりしない。

確認

提出前に、次を確認する。

  1. 原文と一文ずつ照合する。誰が何をするか、数量、時点や順序、例外、不確実さ、義務の強さ、技術的な表記が変わっていないかを見る。
  2. 「一部」「すべて」「場合に限り」などの範囲や制限が変わっていれば直す。近くにある事実同士の関係を勝手に補わない。
  3. 長い文、用語、同じ型の繰り返し、指定の文字数を確認する。本文の全角文字と半角英数字の間に半角スペースを入れる。

見つけた問題を直してから提出する。 推敲の依頼では、依頼やこのルールに合わない箇所だけを直す。 説明を求められなければ、完成した文章だけを返す。 レビューの依頼では、問題箇所、理由、修正案を返す。依頼がなければ全文を書き直さない。

Changes

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.

  1. 3d ago First seen · 47 lines · 26 tokens per session scan A 4be071ffd4a4

Subscribe to this mod's changes

hashiiiii-write-ja is a skill published in the GitHub repository hashiiiii/rules-for-ai (10 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 920 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 2026-09-06.