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 agentmods add skills/decocms/studio/slidesnpx skills add decocms/studio --skill slidesgit clone --depth 1 https://github.com/decocms/studioWhat 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 | $0.00040 | $0.01798 |
| Opus 5 | $0.00020 | $0.00899 |
| Sonnet 5 | $0.00008 | $0.00360 |
| Haiku 4.5 | $0.00004 | $0.00180 |
Grade A, and why
slides 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 2d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
slides — presentation decks
Create and edit presentation decks as single self-contained HTML files,
rendered by Studio's <deck-viewer> runtime. The user gets a live preview
with inline editing, and exports PDF by printing (the deck ships print CSS
— one page per slide; nothing for you to generate).
Quick reference
| Task | How |
|---|---|
| Create a deck | slides-create --data @deck.json --output org/home/decks/<name>.html |
| List themes / templates | slides-create --help |
| See a full data example | cat org/public/core/slides/examples/deck.json |
| Edit an existing deck | read the HTML, edit the <section> slides, write it back |
| Org brand templates | add --templates-dir org/home/templates/slides |
| PDF export | user prints from the preview — no action needed |
Path convention
Decks live at org/home/decks/<name>.html (<name> is lowercase kebab).
Files written there sync to Studio near-instantly and the user sees a live
preview that updates as you work.
Creating a deck
- Read
org/public/core/slides/examples/deck.jsononce to learn the data shapes. - Author your own deck JSON (a file is easier to iterate than inline):
{ "title": …, "theme": …, "slides": [ { "template": …, "data": … } ] } - Render:
slides-create --data @deck.json --output org/home/decks/<name>.html - Iterate content by editing the HTML output (see lifecycle below),
or re-render with
-fonly while the user hasn't touched the deck.
Themes (--theme or "theme" in data; default aurora-light):
aurora-light (clean light, soft gradients), ink-dark (dark keynote,
amber accents), bold-gradient (vivid full-bleed gradient, glass cards).
What ships with it
15 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.
- examples/deck.json 4.0 KB
- slide-templates/agenda.html 225 B
- slide-templates/bullets.html 259 B
- slide-templates/closing.html 197 B
- slide-templates/comparison.html 366 B
- slide-templates/kpi-row.html 394 B
- slide-templates/quote.html 225 B
- slide-templates/section-divider.html 223 B
- slide-templates/timeline.html 393 B
- slide-templates/title.html 267 B
- slide-templates/two-column.html 491 B
- slides-create.mjs 8.0 KB runs code
- themes/aurora-light.html 7.0 KB
- themes/bold-gradient.html 6.5 KB
- themes/ink-dark.html 6.6 KB
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.
- 2d ago First seen · 137 lines · 40 tokens per session scan A c26e48792a04
slides is a skill published in the GitHub repository decocms/studio (401 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,798 once invoked, about $0.0002 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.
Other skills, from other repositories
opengeni
Use when editing, operating, extending, documenting, or debugging the OpenGeni source repository or deployment: architecture, sessions/events, worker orchestration, sandbox backends, files/storage, tools/MCP, scheduling, configuration, and deployment. For a customer product that consumes a standalone OpenGeni…
refactor-module
Transform monolithic Terraform configurations into reusable, maintainable modules following HashiCorp's module design principles and community best practices.
terraform-search-import
Discover existing cloud resources using Terraform Search queries and bulk import them into Terraform management. Use when bringing unmanaged infrastructure under Terraform control, auditing cloud resources, or migrating to IaC.
checkov
Use Checkov to scan Terraform and infrastructure-as-code repositories for policy violations, explain findings, choose safe fixes, rerun scans, and prepare pull requests with remediations.
document-parsing
Extract readable Markdown from local Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and text-based PDF files using the preinstalled AnyDoc runtime.
opengeni-client
Use when an external product, coding agent, CLI, backend, or automation uses a standalone OpenGeni deployment through @opengeni/sdk or @opengeni/react. Covers choosing between a stock-UI handoff, a headless product integration, embedded React session surfaces, or the optional workbench; tenant-safe proxy boundaries…