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-decksgit 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-decks)<a href="https://agentmods.dev/skills/criptogus/hermesoffice/hermesoffice-decks"><img src="https://agentmods.dev/badge/skills/criptogus/hermesoffice/hermesoffice-decks/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-decks"><img src="https://agentmods.dev/badge/skills/criptogus/hermesoffice/hermesoffice-decks.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 | $0.00068 | $0.00539 |
| Opus 5.5 | $0.00027 | $0.00216 |
| Sonnet 5.5 | $0.00014 | $0.00108 |
| Haiku 4.5 | $0.00007 | $0.00054 |
Grade A, and why
hermesoffice-decks 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.
What it actually says
Producing decks
New decks: always through the generation pipeline
For blank/from-scratch decks do not hand-assemble pages element by element — use the pipeline:
-
If the brief is vague,
ask_clarification(audience, goal, tone) or decide with professional judgment. -
Pick a style spec from
templates/decks/and read it:Spec Character modern.mdBold, asymmetric, one idea per slide elegant.mdEditorial serif, muted luxury professional.mdCorporate reviews/QBRs, agenda + summary keynote-speaker.mdStage deck: huge type, dark, no bullets minimal.mdMonochrome, typographic, zero decoration tech-dark.mdDeveloper product: dark UI, code cards investor-pitch.mdFundraising: traction-first, ≤12 slides workshop.mdInteractive session: exercises + timeboxes -
plan_deckwith acore_hook, the spec's Style section asstyle, and the user's content mapped onto the spec's suggested page plan. -
generate_deckonce, passing all planned pages; follow the<generation-progress>notes until every page is done.
Refining an existing deck (native tools)
When the deck already has real content, refine with the element tools:
read_slide for fresh ids, then set_element_text/style/transform/fill/ stroke, edit_table_*, edit_chart, set_slide_background. For
multi-element layout changes use execute_slide_script (atomic, reads real
geometry) and heed the layout-audit warnings it returns.
Data discipline
Charts require a declared dataSource (user / document / search /
sample). search requires an actual web_search in this conversation;
sample data must be explicitly flagged to the user as illustrative.
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 · 46 lines · 68 tokens per session scan A cfbc13efef9c
hermesoffice-decks is a skill published in the GitHub repository criptogus/HermesOffice (618 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 539 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 2026-08-30.
Other skills, from other repositories
cyrene-plan-mode
A planning guide for Cyrene’s Plan Mode, used before code or file changes are made. It helps turn a broad request into an agreed implementation plan based on the project’s actual code and constraints.
cyrene-plugin-dev
A guide for developing runtime plugins for Cyrene, including plugins that add tools, windows, events, live context, or connections to services. Cyrene is the host application that runs these plugins.
cyrene-exam-paper
A method for creating formal exams from a learning plan, then keeping the questions, answers, grading, and review separate. It maps learned topics to skills and suitable question types.
writer-documents
Create, open or edit Writer documents: ODT default; DOCX for Word compatibility.
cyrene-work-hygiene
A Work-mode rulebook for organizing projects that create, arrange, or deliver several files.
cyrene-obsidian-workspace
A set of rules for an agent working with an Obsidian vault, a folder of linked Markdown notes. It defines where materials, notes, exercises, templates, and progress files belong and how they may be edited.