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 commands/nicobailon/visual-explainer/generate-slidesgit clone --depth 1 https://github.com/nicobailon/visual-explainerWhat 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 | $0.00014 | $0.00412 |
| Opus 5 | $0.00007 | $0.00206 |
| Sonnet 5 | $0.00003 | $0.00082 |
| Haiku 4.5 | $0.00001 | $0.00041 |
Grade A, and why
generate-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 3d 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
Load the visual-explainer skill and generate a slide deck for: $@
If $@ contains the literal --pptx flag, remove that flag from the topic. Generate the HTML slide deck first, then run the best-effort static exporter with visual-explainer-pptx <deck.html> <deck.pptx> from package installs or node ./pptx/export.mjs <deck.html> <deck.pptx> from a checkout after dependencies are installed. If the exporter dependencies are not available, deliver the HTML deck and explain that PPTX export needs the package install or checkout dependencies. Tell the user that the HTML deck remains the source of truth and the PPTX will not preserve animations, reader navigation, responsive layout, custom fonts, live Mermaid/Chart.js/SVG/canvas rendering, or JavaScript behavior.
Before writing HTML, read ./templates/slide-deck.html, ./references/slide-patterns.md, and only the shared CSS/library sections needed for the source.
Plan the deck first: inventory the source, map every item to slides, choose a narrative arc, and assign a composition to each slide. Use the 10 slide types and nav chrome from slide-patterns.md/slide-deck.html, including carousel dots, prev/next, slide count, and keyboard controls. Treat 100dvh as a hard content budget: split dense content across slides rather than scrolling or dropping content. Before delivery, enable prefers-reduced-motion: reduce at the target viewport and a short landscape height; fix every overflow or autoFit() warning before shipping.
Use visual-first slides: diagrams, charts, tables, SVG accents, and images from surf only when they clarify the story. Vary compositions; three centered slides in a row is a smell.
Write to ~/.agent/diagrams/ and open in the browser.
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.
- 3d ago First seen · 17 lines · 14 tokens per session scan A 5a5b6c4b3c02
generate-slides is a command published in the GitHub repository nicobailon/visual-explainer (9,621 stars, last pushed 4d ago), licensed MIT. It adds 14 tokens to every session and 412 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.