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.
git clone --depth 1 https://github.com/theclaymethod/artifactureWrote 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/commands/theclaymethod/artifacture/generate-slides)<a href="https://agentmods.dev/commands/theclaymethod/artifacture/generate-slides"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/generate-slides/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/commands/theclaymethod/artifacture/generate-slides"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/generate-slides.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 | $0.00009 | $0.00530 |
| Opus 5.5 | $0.00004 | $0.00212 |
| Sonnet 5.5 | $0.00002 | $0.00106 |
| Haiku 4.5 | $0.00001 | $0.00053 |
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 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 — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Load SKILL.md and cards/slide-deck.md, then present: $@
Slides are opt-in: generate them only when requested or when this command is invoked.
Compose
- Establish the audience, central claim, and source evidence. Use available context and defaults; consult
references/clarify.mdonly for a material unresolved choice. - Plan a sequence in which each slide advances the argument. Start with the conclusion or question, supply evidence, and end with the decision or action the brief requires.
- Use
SlideDeckandSlide. Default to vertical orientation and Lieflat-inspired. Setorientation="horizontal"only for--magazineor an explicit horizontal-magazine request. - Choose composition from the content: comparison, sequence, diagram, data, or focused prose. Preserve reading order and readable labels. Split crowded slides; do not shrink text to fit.
Variation should follow the argument. Do not prescribe dark covers, tint rotation, giant statistics, decorative images, repeated kickers, or a fixed number of card layouts. Use images only when they add evidence or explain something the text cannot.
Read references/slide-patterns.md only for custom mechanics, magazine pacing, or export details. Read references/deck-navigation-shell.md for bespoke fixed-stage navigation and drill-downs.
Deliver
Author MDX/TSX beside ~/.agent/diagrams/<slug>.html (<slug>-magazine.html in magazine mode), export, and complete references/verification.md. Open the result and report source, HTML, final report, and any incomplete output.
--poster-export: also export individual slides as PNGs usingreferences/poster.md→ "Slide decks as per-slide posters". Use browser capture or the availableposterpath; report any export that cannot be completed. Save to~/.agent/diagrams/<slug>/slides/.--pdf: usenode <skill-dir>/scripts/export-slides-pdf.mjs <input.html> <output.pdf>. The exporter captures each slide separately. It requires Playwright and Chromium; seereferences/slide-patterns.md→ "PDF export" for setup and flags. Report missing dependencies instead of silently dropping the PDF.--no-ask: use the request and documented defaults without optional clarification.
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 Changed · -32 lines · -14 tokens per session 95ea439ab307
- 1mo ago First seen · 58 lines · 23 tokens per session scan A ddb80a98d0a4
generate-slides is a command published in the GitHub repository theclaymethod/artifacture (3 stars, last pushed 5d ago), licensed MIT. It adds 9 tokens to every session and 530 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
print-audit
Audit a print layout for bleed, safe zone, color mode, font embedding, and page break rules. Optionally audits brand consistency when brand context is provided.
document
On-demand documentation generation — API docs, architecture updates, user guides.
elaborate-dev
Elaborate a Z specification with narrative from design documentation.
brand-generate
Generate an on-brand document from a saved Brand Profile.
brand-extract
Extract a Brand Profile from an Office template.
generate-report
Generate a professional HTML report from assessment results in the conversation.