natural-japanese is an Agent Skill that helps write and revise clear, readable Japanese for workplace documents. It supports materials such as meeting minutes, research reports, internal guides, proposals, and blog posts by applying writing rules and checking for formulaic phrasing with SudachiPy-based linting. The catalogue includes instructions, a plugin, and a skill related to this writing workflow.
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.
git clone --depth 1 https://github.com/coji/natural-japaneseWrote 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/plugins/coji/natural-japanese/natural-japanese)<a href="https://agentmods.dev/plugins/coji/natural-japanese/natural-japanese"><img src="https://agentmods.dev/badge/plugins/coji/natural-japanese/natural-japanese/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/plugins/coji/natural-japanese/natural-japanese"><img src="https://agentmods.dev/badge/plugins/coji/natural-japanese/natural-japanese.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
natural-japanese 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 today.
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.
What it actually says
{
"name": "natural-japanese",
"description": "仕事の日本語文書を、読みやすくわかりやすく書く・直すためのスキル。議事録・調査レポート・社内ガイド・リサーチメモ・スライド構成などの仕事の文書から、技術記事・PR の説明文・note・ブログ・エッセイまでを扱う。AI らしい書き癖を取り除くことも含む。",
"version": "1.6.3",
"author": {
"name": "coji"
},
"homepage": "https://github.com/coji/natural-japanese",
"repository": "https://github.com/coji/natural-japanese",
"license": "MIT"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 271 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json 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.
- today Changed 0f751b04fb70
- 3d ago Changed 60be09ef222d
- 5d ago Changed b2db3a707993
- 11d ago Changed 4ec6a3c303ec
- 13d ago Changed b36ccf95df56
- 14d ago Changed ac18dbe9f495
- 1mo ago Changed 8d2366233da9
- 1mo ago First seen · 12 lines scan A b0f491c463a6
natural-japanese is a plugin published in the GitHub repository coji/natural-japanese (1,975 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
awesome-japanese-nlp-slides marketplace
Search tools for awesome-japanese-nlp-slides: find Japanese NLP presentation slides and lecture materials.
awesome-japanese-nlp-slides
Search 800+ curated Japanese NLP presentation slides (Speaker Deck, Docswell, SlideShare) and 300+ blog articles / tech-blog posts: tutorials, university lectures, LLM development, RAG, evaluation, and industry case studies. Also finds new slides on the web that the list does not cover yet.
awesome-japanese-nlp-resources
Search 1,450+ Japanese NLP resources: libraries, pretrained models, datasets, tutorials, dictionaries, Hugging Face resources, and multilingual libraries that also support Japanese from awesome-japanese-nlp-resources.
khamlao
ຄຳລາວ (KhamLao) — Lao language quality + compression for Claude. Single skill: quality rules + critical false-friend fixes + built-in vocabulary (everyday/cooking/school/nature). 40-60% token savings.
veritasreason
Full-stack knowledge graph skills: semantic extraction, decision intelligence, context graphs, reasoning, explainability, ontology, provenance, deduplication, visualization, and multi-format export.
humanizer-fr
Réécrit un texte français qui sonne IA pour qu'il se lise comme son auteur, sans changer ce qu'il dit.