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 itarunnn/jp-lit-mcp --skill jp-lit-verificationgit clone --depth 1 https://github.com/itarunnn/jp-lit-mcpWrote 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/itarunnn/jp-lit-mcp/jp-lit-verification)<a href="https://agentmods.dev/skills/itarunnn/jp-lit-mcp/jp-lit-verification"><img src="https://agentmods.dev/badge/skills/itarunnn/jp-lit-mcp/jp-lit-verification/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/itarunnn/jp-lit-mcp/jp-lit-verification"><img src="https://agentmods.dev/badge/skills/itarunnn/jp-lit-mcp/jp-lit-verification.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 | $0.00178 | $0.01244 |
| Opus 5 | $0.00089 | $0.00622 |
| Sonnet 5 | $0.00036 | $0.00249 |
| Haiku 4.5 | $0.00018 | $0.00124 |
Grade A, and why
jp-lit-verification 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 11d 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.
What it actually says
日本語文献実在性調査スキル（jp-lit-verification）
このスキルは、貼り付けた文章に含まれる日本語文献候補の実在性と書誌整合性を検証する。 主入力は、他サービスや他セッションから持ち込まれた回答文・会話ログ・参考文献一覧である。
原則
- 主入力は貼り付け文章
- 文献候補は広めに拾う
- 判定は厳しめに行う
- 主出力は表
- 各行に根拠付きの判定理由を必ず付ける
部分一致/混線の疑いでは、近い候補の著者名・書名・掲載誌または出版社・発行年を可能な限り示す- 一次検証や再確認で
highlights/summary/table_of_contentsが得られた場合は、判定理由や確認候補に短い抜粋を添える ndl_searchを一次検証の第一関門に使う部分一致/混線の疑い/ 再確認価値の高い非実在の疑いだけ、必要なら個別 source で再確認する- 生の検索結果を会話へ大量に貼り付けず、表と判定理由を主に残す
- 重い record / OCR payload は必要時だけ再読込する
- 長い検証では、会話に持ち回るのは要点・怪しい候補・次の手だけに留める
- 候補抽出、一次検証、判定理由の確定は主エージェントが文脈を持って進める
- サブエージェントは任意。単独エージェントで成立することを前提にし、保存済み結果や固定済み候補表の大量再点検・要約に限って使う
フロー
- 貼り付け文章を受け取る
- 文献候補を抽出する
jp_lit_search(source=ndl_search, query=...)で一次検証する- 必要なら個別 source で再確認する
- 表で報告する
コンテキスト運用
ndl_searchの一次検証結果は、表の根拠に必要な要点だけを会話へ残す- 詳細書誌や OCR の再確認が必要なときだけ、個別 source を読み直す
- 重要なのは「何が一致し、何が一致しなかったか」であり、検索結果全文の貼り付けではない
判定カテゴリ
- 実在確認済み
- 部分一致
- 非実在の疑い
- 混線の疑い
出力
主出力は表にする。
| 抽出文献 | 推定タイプ | 検証結果 | 判定理由 | 一致した根拠 | 不一致点 | 確認候補 | 次の手 |
|---|
確認候補 には、可能な限り次を入れる。
- 著者名
- 書名
- 掲載誌名または出版社
- 発行年
- source
- 可能なら
source_idまたは URL
別枠:
文献候補として弱い抽出
- 情報が少なすぎる
- 作品名か文献名か判別しにくい
- 文献候補としては弱いが、抽出対象にはなった
利用ツール
- 一次検証:
jp_lit_search(source=ndl_search, query=...)
- 必要なら個別 source で再確認:
- 図書:
ndl_catalog/cinii_books - 論文:
cinii_articles/jstage_articles/ndl_articles - 一次資料:
ndl_digital
- 図書:
参照順
まず次の reference/ を読む。
- reference/01-core-workflow.md
- reference/02-extraction-and-classification.md
- reference/03-output-and-rationale.md
旧 workflows/ と heuristics/ は移行用の詳細資料として当面残す。
What ships with it
7 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.
- 11d ago First seen · 97 lines · 178 tokens per session scan A c40c21d4c20f
jp-lit-verification is a skill published in the GitHub repository itarunnn/jp-lit-mcp (6 stars, last pushed 5d ago), licensed MIT. It adds 178 tokens to every session and 1,244 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
seedance-examples-ja
This skill should be used when the user asks for Japanese Seedance 2.0 examples, Japanese prompt patterns, example rewrites, or safe versions of working Japanese video-generation prompts.
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
ban-pattern
A design-system rule for recording interface patterns that should not be used because they make a UI look generic or AI-generated.
special-japanese-coder-wife
A coding assistant with a gentle, detail-focused Japanese-inspired companion style. It is designed to read technical information carefully, search for solutions, explain each repair step, and stay patient during difficult work.
suiko
A Japanese writing and review workflow for checking whether text sounds uniform, translated, unnatural, or difficult to read. It supports writing and editing documents such as reports, guides, meeting notes, proposals, and emails.
build-screen
A step-by-step procedure for building one interface screen from a project's existing design contracts. It asks a small number of clarifying questions, creates the screen, and reports what it checked.