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/render-video)<a href="https://agentmods.dev/commands/theclaymethod/artifacture/render-video"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/render-video/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/render-video"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/render-video.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 | $0.00020 | $0.00865 |
| Opus 5.5 | $0.00008 | $0.00346 |
| Sonnet 5.5 | $0.00004 | $0.00173 |
| Haiku 4.5 | $0.00002 | $0.00086 |
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 15d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/render-video
Use /generate-video for a new topic. This route starts from a deck or magazine and follows generate-video.md for audio, checking, encoding, and delivery. Read dynamic-video-authoring.md to turn its source into a moving argument.
Honor the requested style, voice, duration, and script. Preserve facts, units, important encodings, and explicit visual identity. Use clarify.md for material unknowns; honor answered choices and existing authorization.
Recover the explanation
For MDX/TSX, read the editable source and export it before inspecting the HTML. For an HTML-only scroll-snap deck or horizontal magazine, identify .slide / .page units, claims, figures, supporting evidence, relationships, and meaningful interactive states. Other presentation structures need an inspected adapter; this route does not promise arbitrary React-child conversion.
Find the viewer's question and its mechanism. Source slides contain evidence; film beats follow the explanation. Merge repeated claims, separate overloaded proof, and record omitted material in delivery notes. A reel needs a compact argument with an immediate event and completed consequence.
Reuse source owners for motion
Reuse existing GraphicScene / GraphicSlide geometry and semantic IDs when available. Compile meaningful events on those scenes and export one sequenceSlides sequence. Keep deck navigation and reading-only controls outside the film.
| Source | Animated treatment |
|---|---|
| Diagram | Trace a request/dependency, reveal its causal edge, transfer focus at arrival, and show the consequence. |
| Code / diff | Bind exact source ranges, edit the responsible condition with retained character identity, then replay the input. |
| Before / after | Register common geometry and use a comparison wipe; do not imply relayout or arbitrary morphing. |
| Data / table | Preserve the unit/record encoding and reveal the records or comparison supporting the finding. |
| Layers / ownership | Follow a task across boundaries or separate meaningful parts with an exploded assembly. |
| Mathematics | Construct the relationship and couple its consequences to one variable; use Manim for required formula transforms. |
| Photograph / native clip | Preserve provenance and timing, place it in the source-owned delivery layer, and keep labels readable. |
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.
- 15d ago Changed · -83 lines · +4 tokens per session fde6e7aeade1
- 17d ago Changed · +4 lines 1f03cf89c2a1
- 1mo ago Changed · -16 lines 67e5a7216442
- 1mo ago First seen · 140 lines · 16 tokens per session scan A 3a67413109e8
render-video is a command published in the GitHub repository theclaymethod/artifacture (3 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 865 once invoked, about $0.0001 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
learn
Force claude-smart to extract learnings from this session now.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
init
Install the formatters this repository needs, with every command visible before it runs.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.