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/render-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 | $0.00016 | $0.01833 |
| Opus 5 | $0.00008 | $0.00916 |
| Sonnet 5 | $0.00003 | $0.00367 |
| Haiku 4.5 | $0.00002 | $0.00183 |
Grade A, and why
render-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 yesterday.
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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/render-video
Take an existing HTML output — a slide deck from /generate-slides, a magazine from /generate-slides --magazine, or any self-contained HTML deck with scroll-snap sections — and render it as an MP4 via Hyperframes.
Input: a path to an HTML file already generated by this skill.
Output: one MP4 in ~/.agent/videos/<slug>.mp4 plus 3 keyframe PNGs.
Cost: medium — wall-clock dominated by per-slide entrance animations × slide count.
Source/artifact contract. Render generated HTML artifacts. If the user gives a .mdx or .tsx deck source, export it first with npm run ve:export. If the render requires a custom Hyperframes composition, write that composition as TSX and export static generated HTML with npm run ve:export-static -- <composition.tsx> --out ~/.agent/videos/<slug>/index.html. The generated HTML is the Hyperframes input artifact; the editable source remains MDX/TSX.
This is different from /generate-video:
/generate-videostarts from a topic and builds a Hyperframes composition from scratch/render-videostarts from existing HTML and translates slides → compositions
Workflow
1. Clarify
Video is high-cost. Always confirm via AskUserQuestion unless the user passes --no-ask:
- Style: long-form (16:9, scene-per-slide, slide dwell times) or reel (9:16, compress to 6–8 beats, hard cuts)
- Narration:
auto(TTS from slide copy),<script>(user-provided),none(silent) - Duration target if narration is
noneorauto— per-slide dwell in long-form mode
2. Check prerequisites
bash {{skill_dir}}/scripts/hyperframes-doctor.sh
The doctor also probes the upstream /hyperframes + /hyperframes-cli + /gsap skills and warns (non-fatal) if missing. When present, delegate vocab and plumbing to them. When absent, author directly from references/hyperframes.md, references/gsap-rules.md, and references/reel-patterns.md. See references/hyperframes.md → "Delegation boundary".
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.
- yesterday First seen · 140 lines · 16 tokens per session scan A 3a67413109e8
render-video is a command published in the GitHub repository theclaymethod/artifacture (2 stars, last pushed 9d ago), licensed MIT. It adds 16 tokens to every session and 1,833 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.
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.