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 ilia-sokolov/OfficeAgent.NET --skill officeagent-integrationgit clone --depth 1 https://github.com/ilia-sokolov/OfficeAgent.NETWrote 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/ilia-sokolov/officeagent.net/officeagent-integration)<a href="https://agentmods.dev/skills/ilia-sokolov/officeagent.net/officeagent-integration"><img src="https://agentmods.dev/badge/skills/ilia-sokolov/officeagent.net/officeagent-integration/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/ilia-sokolov/officeagent.net/officeagent-integration"><img src="https://agentmods.dev/badge/skills/ilia-sokolov/officeagent.net/officeagent-integration.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 | $0.00070 | $0.01004 |
| Opus 5.5 | $0.00028 | $0.00402 |
| Sonnet 5.5 | $0.00014 | $0.00201 |
| Haiku 4.5 | $0.00007 | $0.00100 |
Grade A, and why
officeagent-integration 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 yesterday.
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.
OfficeAgent.NET integration
Use OfficeAgent.NET only when its typed OOXML operations and preservation boundaries match the application. Start with the direct .NET API. Add MCP or Microsoft Agent Framework only when the host needs model tool calling.
Route the request
- For dependency selection, application wiring, package installation, providers, MCP, or agent tools, continue with this skill.
- For an agent actively reviewing or editing an existing Word document, use
word-document-reviewafter the host integration is ready. - For unsupported formats, native Office layout, a full Excel calculation engine, or low-level OOXML operations outside the documented plan operations, choose another component or use the Open XML SDK directly. The optional
OfficeAgent.Excel.Calculationpackage fills in cached formula values for an allowlisted set of functions and reports every formula it does not calculate; it does not replace Excel's own calculation. When both are needed in one application, follow the tested copy, edit, reinspect workflow in the versioned SDK interoperability guide and recipe 4 of recipes.
Read the versioned selection guide before choosing packages. Keep all OfficeAgent packages on the same version.
Build in this order
- Choose only the format modules the application needs. Direct Word work normally needs
OfficeAgent.CoreandOfficeAgent.Word. - Choose a bounded input model. Use
StreamHandlewhen the caller owns bytes, or configure a provider when the workflow needs stable document ids and saved outputs. - Inspect and find before authoring a plan. Carry the inspection snapshot into the plan when covered-content drift must be detected.
- Preview the complete plan and handle every error before commit. Never treat preview as a future-write guarantee.
- Commit, retrieve the canonical output, and assert document semantics. Structural schema checks do not replace native Office or visual review.
- Add the optional interface only after the direct workflow passes:
OfficeAgent.AgentFrameworkexposesAIFunctiontools over the same client.OfficeAgent.Mcphosts the same engine over stdio or streamable HTTP.
What ships with it
5 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.
- yesterday Changed 185a92dafb7f
- 3d ago Changed 4015974bca68
- 15d ago Changed 4199fba9c731
- 22d ago Changed 2578cb543a97
- 25d ago First seen · 51 lines · 70 tokens per session scan A 280ccd29ba65
officeagent-integration is a skill published in the GitHub repository ilia-sokolov/OfficeAgent.NET (27 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 1,004 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-21.
Other skills, from other repositories
aos-agent-skill-document
A document-publishing workflow for planning, creating, converting, checking, and preparing reports, proposals, manuals, white papers, and brand documents for release.
aos-process-pdf
Create, inspect, render, compare, clean, and visually verify professional PDF files while preserving fixed-layout fidelity. Use when Codex needs print-ready exports, PDF metadata and page-geometry inspection, page rendering, contact sheets, structural checks, public-release QA, or validation of PDF output converted…
aos-publish-document
Coordinate end-to-end professional document publishing across editable Word and fixed PDF deliverables. Use when Codex needs to turn source materials into publication-ready reports, white papers, proposals, manuals, brand books, or other business documents through content planning, DOCX authoring, PDF conversion…
genoffice
Create, convert, read and edit Office documents locally with GenOffice's command line. Build a new presentation (pptx) from a brief through a checked outline, per-page spec and render pipeline, a new spreadsheet (xlsx) from CSV or JSON data with formulas, a new Word document (docx) from Markdown or HTML, or a PDF…
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. This is the generic document-writing engine (tool surface, tagged-value shapes, fabrication rules). For the four standard NetClaw report…
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…