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-video)<a href="https://agentmods.dev/commands/theclaymethod/artifacture/generate-video"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/generate-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/generate-video"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/generate-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 | $0.00028 | $0.02338 |
| Opus 5.5 | $0.00011 | $0.00935 |
| Sonnet 5.5 | $0.00006 | $0.00468 |
| Haiku 4.5 | $0.00003 | $0.00234 |
Grade A, and why
generate-video scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/generate-video
Turn a topic, inspected change, outline, or source document into an editable animated film. Deliver the MP4, source, timing/claim receipts, and decoded review frames. Use the installed CLI from the skill directory; obtain its ready runtime with REPO=$(node "$SKILL_DIR/scripts/artifacture.mjs" path).
Read dynamic-video-authoring.md before writing the story. It teaches narrative modes, implemented primitive choices, continuous subjects, choreography, narration alignment, and film review. Read motion-video-baseline.md for Hairline / 3b1b styling. Explicit user styling takes precedence.
Establish the moving argument
Honor the supplied audience, voice, scope, duration, and session authorization. Infer ordinary choices. Use clarify.md only for a material unresolved choice; continue independent work while it is pending.
For a code review, pin the exact PR/diff base and head and bind claims to inspected files and observed checks. Show the trigger, changed owner or condition, architectural consequence, proof, and remaining boundary. Replay the input after a correction. For a nontechnical film, maintain the analogy's correspondence and explain its limit. For a sizzle reel, give each showcased capability a complete, recognizable action.
Mode is the viewer's task, style is the delivery format, and engine is the renderer. Print canonical mode fields with npm --prefix "$REPO" run ve:video-collection -- modes. Read video-collections.md for shared episodes or mode-specific briefs. Scaffolding creates editable drafts; validation does not approve the script or finish the film. Honor the session's script approval or autonomous iteration preferences.
| Style | Starting format | Compose for |
|---|---|---|
long-form |
1920×1080, 16:9, 30fps; usually 60–180s | A question, a visible mechanism, evidence, and a readable conclusion. Narration determines timing. |
reel |
1080×1920, 9:16, 30fps; usually 30–60s | An immediate event and dense, readable progression. Use 16:9 when requested for desktop sharing. |
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.
- 14d ago Changed · +13 lines 15b63e3669c9
- 15d ago Changed · -104 lines · +10 tokens per session b19a65e7fc26
- 16d ago Changed · -1 lines e13a0433cc71
- 17d ago Changed · +19 lines 6a1656e9b24e
- 1mo ago Changed · -8 lines a74775b045ff
- 1mo ago First seen · 184 lines · 18 tokens per session scan A 4b7e5a0bd888
generate-video is a command published in the GitHub repository theclaymethod/artifacture (3 stars, last pushed 5d ago), licensed MIT. It adds 28 tokens to every session and 2,338 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.