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 axutse/aos-agent-skill-document --skill aos-publish-documentgit clone --depth 1 https://github.com/axutse/aos-agent-skill-documentWrote 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/axutse/aos-agent-skill-document/aos-publish-document)<a href="https://agentmods.dev/skills/axutse/aos-agent-skill-document/aos-publish-document"><img src="https://agentmods.dev/badge/skills/axutse/aos-agent-skill-document/aos-publish-document/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/axutse/aos-agent-skill-document/aos-publish-document"><img src="https://agentmods.dev/badge/skills/axutse/aos-agent-skill-document/aos-publish-document.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 | $0.00099 | $0.00739 |
| Opus 5 | $0.00049 | $0.00369 |
| Sonnet 5 | $0.00020 | $0.00148 |
| Haiku 4.5 | $0.00010 | $0.00074 |
Grade A, and why
aos-publish-document 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AOS Document Publishing
Produce polished documents through a deterministic plan -> author -> render -> inspect -> revise -> verify loop.
Match the user's requested language. When the user requests Chinese and English editions, read references/bilingual-delivery.md and verify each language artifact independently.
Position the work
Act as a document publishing orchestrator, not as a replacement for Word, Acrobat, factual review, legal review, or rights clearance. Combine Codex reasoning with local document tools, preserve editability where required, and treat rendered-page verification as part of the deliverable rather than an optional preview.
Read references/positioning-and-routing.md when selecting among the three AOS skills, explaining scope to the user, or defining the input and output contract.
Route the work
- Use
$aos-author-wordwhen editability, semantic styles, tracked document structure, or DOCX delivery matters. - Use
$aos-process-pdffor fixed-layout creation, PDF inspection, metadata checks, rendering, page operations, or print-ready verification. - Use both when the user requests DOCX and PDF: author the DOCX first, verify it, export the PDF, and verify the PDF again.
- Do not invoke all three skills mechanically. Use this skill as the orchestration entry point and load the format-specific workflow only when the task requires it.
Required workflow
- Inspect all supplied sources before drafting.
- Confirm format, page size, language, editability, style, and delivery requirements from context.
- Build a section and page plan for long documents.
- Preserve verified names, figures, terminology, and source meaning. Mark simulated values clearly.
- Apply a coherent editorial system. Read references/editorial-design.md for premium reports and white papers.
- Render the complete final document.
- Inspect every page at readable zoom; a contact sheet is only an overview.
- Fix clipping, overlaps, broken tables, missing glyphs, blurry images, weak hierarchy, and incorrect headers or footers.
- Re-render after each layout-sensitive change.
- Run metadata and secret checks before public release.
- Deliver only requested final artifacts unless QA outputs are requested.
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 · 51 lines · 99 tokens per session scan A d95d6f345f55
aos-publish-document is a skill published in the GitHub repository axutse/aos-agent-skill-document (2 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 739 once invoked, about $0.0005 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
document-generation
Generate Word (.docx), Excel (.xlsx) and PowerPoint (.pptx) documents and fill existing PDF forms, from real NetClaw data, with per-element provenance and no fabrication. Use when someone needs a deliverable rather than an answer — a change record to attach to a CR, an audit workbook for a compliance reviewer, a…
document-processing
Use when the deliverable is a document's bytes or its literal content — text/tables out of PDFs, AcroForm fill and flatten, page merge/split, PDF/DOCX from templates, OCR of image-only scans. NOT schema-typed fields pulled from text (that is structured-extraction), NOT signature routing (e-signature) or spreadsheet…
docx
Read, create, and convert Microsoft Word (.docx) documents — extract text and tables, build reports from markdown/JSON, and export to PDF.
document-processing-expert
Read, generate and modify office documents and PDFs from code: PDF extraction and forms, Word documents, Excel workbooks and PowerPoint decks. Use when the user mentions PDF, DOCX, XLSX, PPTX, Word, Excel, PowerPoint or spreadsheets, wants data extracted from documents, needs a report or invoice generated as a file…
bank-statement-parsing
Guidelines for parsing bank statements using YOLO layout detection + OCR + LLM.
word-document-review
Review and edit existing Word documents (.docx) through OfficeAgent with tracked changes, comments, revision decisions, table updates, footnotes, or page-layout changes. Use when a user asks to revise, redline, mark up, or resolve review state in an existing Word file. Do not use for read-only extraction…