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/theclaymethod/artifacture/generate-videogit clone --depth 1 https://github.com/theclaymethod/artifactureWhat 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 | $0.00018 | $0.02205 |
| Opus 5 | $0.00009 | $0.01103 |
| Sonnet 5 | $0.00004 | $0.00441 |
| Haiku 4.5 | $0.00002 | $0.00220 |
Grade A, and why
generate-video 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/generate-video
Generate an explainer video from scratch. Wraps Hyperframes (local HTML → MP4 renderer) with specialized modes for explainer content.
Input: a topic, outline, or source document.
Output: one MP4 in ~/.agent/videos/<slug>.mp4 plus 3 keyframe PNGs for review.
Cost: medium — render wall-clock is typically 30s–5min depending on duration and quality.
Authoring contract. Prefer React TSX composition source. Write the editable Hyperframes composition as .tsx, register a synchronous paused GSAP timeline on window.__timelines["<id>"], then export static generated HTML with:
npm run ve:export-static -- <composition.tsx> --out ~/.agent/videos/<slug>/index.html
The generated index.html is the Hyperframes input artifact, not the source of truth. Apply revisions to the TSX composition and re-export before lint, validate, or render. The legacy templates/hyperframes-*.html files are reference material for timing, layout, and GSAP structure; do not hand-write final Hyperframes HTML unless the React static export path is blocked and you explicitly report that fallback.
Styles
Two styles, picked via --style or confirmed via AskUserQuestion.
long-form (default when unsure)
- Aspect: 16:9 landscape, 1920×1080
- Duration: 60–180 seconds
- Pacing: Slide-paced, 10s average dwell per scene, 6–12 scenes
- Audience: Team meetings, onboarding, LinkedIn, docs embeds
- Reference template:
templates/hyperframes-longform.html - Animations: Fade-ups, count-ups, cross-fades between scenes, optional shader transitions at major beat boundaries
- Audio: TTS narration over dwell scenes; optional soft bed
reel (supports two aspect ratios)
- Aspect:
--aspect=9:16(default, vertical 1080×1920) OR--aspect=16:9(landscape 1920×1080) - Duration: 30–60 seconds (default 45s)
- Pacing: Hard cuts every 1.2–1.8s; 6–8 beats; hook within 2s
- Audience — 9:16: Shorts / Reels / TikTok silent-autoplay feeds
- Audience — 16:9: X/Twitter embeds, LinkedIn, YouTube-embedded, desktop shares, conference intro stings
- Reference templates:
templates/hyperframes-reel.html(9:16)templates/hyperframes-reel-landscape.html(16:9)
- Animations: Kinetic typography (word-by-word), progressive diagram reveal, Ken Burns on imagery, shader transitions at beat boundaries. 16:9 MECHANISM beats use native split-screen (before/after side-by-side) instead of vertical stacks.
- Audio: TTS narration with burned-in captions; safe zones adapt (9:16 bottom 200px for phone chrome and caption clearance, 16:9 bottom 140px for a centered caption pill)
- Read:
references/reel-patterns.md§ Two aspect ratios — authoritative guide for picking between 9:16 and 16:9 and the layout rules that differ between them.
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 · 184 lines · 18 tokens per session scan A 4b7e5a0bd888
generate-video is a command published in the GitHub repository theclaymethod/artifacture (2 stars, last pushed 9d ago), licensed MIT. It adds 18 tokens to every session and 2,205 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 2026-08-31.
Other commands, from other repositories
editor
You are my personal writing editor for MDX/Markdown content. Improve clarity, flow, grammar, and style while preserving the author's voice, meaning, and factual details. Infer the content type and appropriate tone from the context.
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.
constitution
Create or update the project constitution from interactive or provided principle inputs.