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 criptogus/HermesOffice --skill hermesoffice-documentsgit clone --depth 1 https://github.com/criptogus/HermesOfficeWrote 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/criptogus/hermesoffice/hermesoffice-documents)<a href="https://agentmods.dev/skills/criptogus/hermesoffice/hermesoffice-documents"><img src="https://agentmods.dev/badge/skills/criptogus/hermesoffice/hermesoffice-documents/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/criptogus/hermesoffice/hermesoffice-documents"><img src="https://agentmods.dev/badge/skills/criptogus/hermesoffice/hermesoffice-documents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00057 | $0.00564 |
| Opus 5.5 | $0.00023 | $0.00226 |
| Sonnet 5.5 | $0.00011 | $0.00113 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
hermesoffice-documents 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 1mo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Producing documents
Editing the open document (in-app tools)
- Orient first:
get_document_context, thenread_blocksfor the regions you will touch. - Edit at block granularity:
replace_blocks/insert_content/apply_commands. Only reference styles that already exist in the document. - Respect tracked changes: when the document has revisions enabled, your edits are recorded as proposals for the user to accept — do not try to bypass that.
- Charts and images:
insert_chartneeds real data (from the document, the user, orweb_search); never invent figures.
Creating a new document (file-level tools)
Flow for "write me a report / plan / memo":
-
Read the sources (
hermesoffice_extract_texton the referenced files, or the in-app read tools). -
Pick the closest template from
templates/docs/and follow its structure:Template Use for meeting-notes.docxMinutes: agenda, decisions, action items idea-brief.docxPitching a concept and its next experiment business-plan.docxFull plan through financials and the ask project-proposal.docxScoped proposal with milestones and risks status-report.docxWeekly status: TL;DR, done/planned, blockers product-requirements.docxPRD: stories, requirements, rollout decision-memo.docxOptions table + recommendation + decision record one-pager.docxSingle-page executive summary with an ask -
Replace every
[placeholder]and italic guidance line with real content; keep the heading structure; delete the template note. -
Write the result as a new
.docx(hermesoffice_docx_create), open it withhermesoffice_app_open_file, and reply with the path.
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.
- 1mo ago First seen · 50 lines · 57 tokens per session scan A ccb8580d12c0
hermesoffice-documents is a skill published in the GitHub repository criptogus/HermesOffice (614 stars, last pushed 23d ago), licensed Apache-2.0. It adds 57 tokens to every session and 564 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
writer-documents
Create, open or edit Writer documents: ODT default; DOCX for Word compatibility.
office-open
Generate, parse, and patch Office Open XML documents (.docx, .pptx, .xlsx) using pure JSON options and functional API. Use when creating Word documents, PowerPoint presentations, or Excel spreadsheets with TypeScript — paragraphs, tables, images, charts, shapes, math equations, headers, footers, styles, effects…
document-creator
Use when creating, editing, and generating Office documents programmatically — Word, PowerPoint, Excel, and PDF. One interface for all document formats with shared methodology.
docx
Create, read, edit, or review Word documents (.docx), including styles, tables, headers, tracked changes, and comments. Use when Word is the input or required deliverable.
anywrite
Compiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.
akf-trust-metadata
The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA aud.