office-word

office-word is a skill for Claude Code, Codex from Orkas-AI/Orkas. It costs 2 tokens per session (764 once invoked), scanned A, original, MIT.

A skill for creating and editing Microsoft Word .docx files with bundled office tools. It can inspect document structure, apply text or element changes, and review the result.

In plain words
What is it for?
Use it to read document metadata, create new .docx files, make targeted edits, and check or render representative pages.
Why use it?
It provides a defined way to work with Word documents while avoiding unsupported legacy .doc files and unsafe macros. Reviewing the output helps catch layout or structural problems.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to read document metadata, create new .docx files, make targeted edits, and check or render representative pages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orkas-ai/orkas/c72c656eca12
About the project

Orkas is a desktop application for commanding a team of AI agents through one chat, with a commander model assigning work to specialist agents in parallel or in sequence. People use it to coordinate research, writing, presentations, and software tasks while keeping files on their computer. The catalogue includes skills for extending the agents available to Orkas.

Orkas-AI/Orkas · 1,885 stars · on GitHub · orkas.ai

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 Orkas-AI/Orkas --skill c72c656eca12
Clone the repo
git clone --depth 1 https://github.com/Orkas-AI/Orkas

Made for: Claude Code, 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 office-word

README.md
[![agentmods](https://agentmods.dev/badge/skills/orkas-ai/orkas/c72c656eca12/github.svg)](https://agentmods.dev/skills/orkas-ai/orkas/c72c656eca12)
Your own site
<a href="https://agentmods.dev/skills/orkas-ai/orkas/c72c656eca12"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/c72c656eca12/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 office-word

Your own site · 80×15
<a href="https://agentmods.dev/skills/orkas-ai/orkas/c72c656eca12"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/c72c656eca12.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 764 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00002 $0.00764
Opus 5 $0.00001 $0.00382
Sonnet 5 $0.00000 $0.00153
Haiku 4.5 $0.00000 $0.00076

Measured 11d ago against content hash 04ee85a5ea8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

office-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.

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.

resources/builtin/marketplace/skills/c72c656eca12/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Office Word

Tool Route

Use the bundled Office tools as the default path. Do not install OfficeCLI or document libraries when these tools are available.

  • Use read_files with one paths item for broad text inspection; use metadata_only:true when only prepared metadata is needed.
  • Use create_docx for a new .docx.
  • Use office_read to discover stable element paths before a precise edit.
  • Pass the pre-existing source to edit_office; it creates the separate -edited working copy automatically. Never copy or edit the user's only source yourself.
  • After every create or edit, use office_review with action:"check_and_render" on representative pages when layout matters, or action:"check" for structural-only validation.

The built-in engine supports .docx, not legacy .doc. Require conversion before editing a legacy file. Do not execute macros or embedded code.

edit_office.operations accepts only set, add, and remove. For a path-targeted text replacement, use this exact shape after office_read:

{
  "path": "contract-reviewed.docx",
  "operations": [
    {
      "action": "set",
      "path": "/body/p[2]",
      "props": {
        "find": "旧辰科技有限公司",
        "replace": "星河科技有限公司"
      }
    }
  ]
}

Do not invent a replace action, an edits field, or top-level find / replace fields. Omit output_path when the automatic -edited name is acceptable.

Preservation Rules

  1. Inspect styles, numbering, relationships, sections, headers/footers, fields, comments, and revisions before editing an existing document.
  2. Change the smallest safe element. Preserve bookmarks, comment anchors, revision blocks, numbering definitions, fields, section settings, and relationship files unless the user requests otherwise.
  3. For new documents, use named heading/body styles and explicit page size, margins, table widths, and section settings. For documents containing CJK text, explicitly name CJK-capable fonts for those styles; do not rely on an unspecified “Chinese font” or renderer fallback.
  4. Treat tracked changes, comments, fields, and complex layout as fidelity-sensitive. If the exposed tool contract cannot express the requested operation safely, report the limitation instead of falling back to an unreviewed package or raw XML rewrite.

Read the full file on GitHub · 59 lines

Files

What ships with it

1 file 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 · 59 lines · 2 tokens per session scan A 04ee85a5ea8c

Subscribe to this mod's changes

office-word is a skill published in the GitHub repository Orkas-AI/Orkas (1,885 stars, last pushed today), licensed MIT. It adds 2 tokens to every session and 764 once invoked, about $0.0000 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.