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 AnyGenIO/anygen-selected-skills --skill jp-reportgit clone --depth 1 https://github.com/AnyGenIO/anygen-selected-skillsWrote 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/anygenio/anygen-selected-skills/jp-report)<a href="https://agentmods.dev/skills/anygenio/anygen-selected-skills/jp-report"><img src="https://agentmods.dev/badge/skills/anygenio/anygen-selected-skills/jp-report/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/anygenio/anygen-selected-skills/jp-report"><img src="https://agentmods.dev/badge/skills/anygenio/anygen-selected-skills/jp-report.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 | $0.00048 | $0.00891 |
| Opus 5 | $0.00024 | $0.00445 |
| Sonnet 5 | $0.00010 | $0.00178 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
jp-report 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 12d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate a formal Japanese corporate document (日本企業向け正式報告書) from the provided source material.
INPUTS
If $ARGUMENTS is provided, treat it as the source file path or inline content.
Otherwise, ask the user for:
- Source material — file path or pasted content
- Document purpose — e.g. security overview / compliance / product explanation
- Japanese title + English subtitle
- Classification level — 社外秘 / 部外秘 / 社内限り (default: 社外秘)
- Output folder path
- Revision number (default: Rev. 1.0)
STEP 1 — ANALYZE
Read source material. Identify:
- Logical sections → map to 4–6 chapters
- Content types: principles, tables, architecture diagrams, bullet lists
- Brand names / technical terms to preserve verbatim
- Content to exclude (confirm with user if unclear)
STEP 2 — TRANSLATE TO FORMAL JAPANESE
Rewrite all content in 書き言葉・敬体:
- Verb endings: 〜しております / 〜いたします / 〜となっております
- Full grammatical sentences — no fragment bullets inside tables or definitions
- Preserve intact: brand names, acronyms (RBAC, TLS, SSO, BYOK), product names
- Do NOT add certifications (SOC/ISO/GDPR) unless explicitly in source
STEP 3 — PLAN PAGES
Fixed structure:
Page 1 — 表紙 (Cover) : centered layout, one full A4 page
Page 2 — 目次 (TOC) : dotted leaders + page numbers, one full A4 page
Page 3+ — 本文 (Body) : chapters distributed, target one chapter per page
Numbering: 第1章 / 第2章 … (full-width) · Sections: 1.1 / 1.2 … (decimal)
Before writing HTML, calculate content height using the reference in ${CLAUDE_SKILL_DIR}/docs/design-rules.md.
Usable area per page ≈ 980px. State the page plan briefly to the user.
STEP 4 — GENERATE HTML
Write a single self-contained .html file using:
- CSS from
${CLAUDE_SKILL_DIR}/docs/design-rules.md(include verbatim in<style>) - Component HTML from
${CLAUDE_SKILL_DIR}/docs/components.md
Every page must follow this shell:
<div class="page">
<div class="page-body"> <!-- content --> </div>
<div class="page-footer">
<div class="f-l">[Product / Company]</div>
<div class="f-c">[Document title] Rev. X.X</div>
<div class="f-r">[Classification] | [Page #]</div>
</div>
</div>
What ships with it
6 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.
- 12d ago First seen · 103 lines · 0 tokens per session scan A 0c5984dbd46a
jp-report is a skill published in the GitHub repository AnyGenIO/anygen-selected-skills (11 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 891 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.