aos-author-word

aos-author-word is a skill for Codex from axutse/aos-agent-skill-document. It costs 105 tokens per session (535 once invoked), scanned A, original, MIT.

A workflow for creating, editing, inspecting, converting, and visually checking editable Microsoft Word documents. It preserves Word structure such as styles, tables, sections, headers, and footers.

In plain words
What is it for?
Use it to author or revise reports, proposals, manuals, policies, and other professional Word documents, then inspect, render, and clean their metadata.
Why use it?
It helps prevent layout damage and hidden document problems when changing or publishing DOCX files.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit Use it to author or revise reports, proposals, manuals, policies, and other professional Word documents, then inspect, render, and clean their metadata.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/axutse/aos-agent-skill-document/aos-author-word
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 axutse/aos-agent-skill-document --skill aos-author-word
Clone the repo
git clone --depth 1 https://github.com/axutse/aos-agent-skill-document

Made for: Codex.

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 aos-author-word

README.md
[![agentmods](https://agentmods.dev/badge/skills/axutse/aos-agent-skill-document/aos-author-word/github.svg)](https://agentmods.dev/skills/axutse/aos-agent-skill-document/aos-author-word)
Your own site
<a href="https://agentmods.dev/skills/axutse/aos-agent-skill-document/aos-author-word"><img src="https://agentmods.dev/badge/skills/axutse/aos-agent-skill-document/aos-author-word/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 aos-author-word

Your own site · 80×15
<a href="https://agentmods.dev/skills/axutse/aos-agent-skill-document/aos-author-word"><img src="https://agentmods.dev/badge/skills/axutse/aos-agent-skill-document/aos-author-word.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 535 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 $0.00105 $0.00535
Opus 5 $0.00053 $0.00267
Sonnet 5 $0.00021 $0.00107
Haiku 4.5 $0.00011 $0.00053

Measured 11d ago against content hash e9f614afc973, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

aos-author-word 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.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/inspect_docx.py, scripts/lo_convert_to_pdf.py, scripts/render_docx.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/aos-agent-skill-document/skills/aos-author-word/SKILL.md · 41 lines

What it actually says

AOS Word Authoring

Use semantic Word structure and complete visual verification. Read references/docx-workflow.md before complex authoring or section work.

Treat DOCX editability and preservation of existing structure as the primary contract. Do not rebuild an entire document when the user requests localized edits, and do not claim complete visual QA when LibreOffice rendering is unavailable.

Workflow

  1. Preserve the original file and make localized changes for edit requests.
  2. Use python-docx for normal authoring and targeted OOXML only where required.
  3. Use real paragraph styles, list definitions, sections, headers, footers, and native tables.
  4. Set explicit page geometry, margins, image size, and table widths instead of relying on defaults.
  5. Run set_docx_high_fidelity.py before final rendering.
  6. Run inspect_docx.py and resolve unexpected metadata, sections, media, or settings.
  7. Render the DOCX with render_docx.py and inspect every PNG page.
  8. Re-render after each layout-sensitive change.
  9. Run scrub_docx_metadata.py before external publication when personal metadata is not required.

Commands

python scripts/inspect_docx.py input.docx --json
python scripts/set_docx_high_fidelity.py input.docx output.docx
python scripts/scrub_docx_metadata.py input.docx public.docx
python scripts/render_docx.py public.docx --output-dir render --emit-pdf
python scripts/lo_convert_to_pdf.py public.docx output.pdf

Quality rules

  • Do not deliver a DOCX solely because text extraction succeeds.
  • Inspect every rendered page for clipping, overlaps, glyph substitution, broken tables, image blur, page breaks, headers, footers, and numbering.
  • Keep tables editable and images proportional.
  • Remove comments, tracked changes, private metadata, and placeholders unless the user requests them.
  • If LibreOffice is unavailable, perform structural QA and disclose that render QA could not run.
Files

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.

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. 11d ago First seen · 41 lines · 105 tokens per session scan A e9f614afc973

Subscribe to this mod's changes

aos-author-word is a skill published in the GitHub repository axutse/aos-agent-skill-document (2 stars, last pushed 29d ago), licensed MIT. It adds 105 tokens to every session and 535 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.

Related

Other skills, from other repositories

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…

ilia-sokolov/OfficeAgent.NET · 78 tokens

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…

automateyournetwork/netclaw · 91 tokens

hermesoffice-documents

Produce and edit Word documents in HermesOffice Docs — block editing, tracked changes, reports, and the templates/docs library (meeting notes, business plan, PRD, decision memo, and more). Load for any request that creates or restructures a document.

criptogus/HermesOffice · 57 tokens

hermesoffice

Core conventions for working inside the HermesOffice suite (Docs, Sheets, Slides, PDF) — session continuity, tool selection, and the save-and-reload contract. Load whenever a request originates from a HermesOffice AI panel or targets an office document on this machine.

criptogus/HermesOffice · 57 tokens

office-artifacts

Manage Office files, formats and versions; use Writer, Calc or Impress for content.

agent0ai/agent-zero · 21 tokens

writer-documents

Create, open or edit Writer documents: ODT default; DOCX for Word compatibility.

agent0ai/agent-zero · 22 tokens