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 skills/jangles-byte/atelier/generative-motionnpx skills add jangles-byte/atelier --skill generative-motiongit clone --depth 1 https://github.com/jangles-byte/atelierWhat 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 | $0.00150 | $0.01276 |
| Opus 5 | $0.00075 | $0.00638 |
| Sonnet 5 | $0.00030 | $0.00255 |
| Haiku 4.5 | $0.00015 | $0.00128 |
Grade A, and why
generative-motion scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
warping, curl. Most beautiful motion is a field being sampled. How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generative Motion
The gap between a generative sketch and a generative artwork is almost never the algorithm — the algorithms are public and short. It is art direction: what the colour means, where the density sits, how slowly it evolves, and what you left out.
A tutorial renders the algorithm. A piece renders a decision.
Workflow
- Write the intent first, in two or three sentences: what the system is (embers on
a thermal, ink in water, a colony finding food), what the viewer should feel, and the
one property that earns colour. Skipping this is what produces rainbow noise.
The
design-directionskill's philosophy format applies directly. - Pick the system from references/systems.md — each entry
has the equations, the parameter ranges that actually look good, and its failure mode.
Its numbers are machine-checked:
validate/attractors.pyandvalidate/gray_scott.pyverify every attractor seed and reaction–diffusion pair on CPU in seconds. Run them after changing any value, and use them to find your own. - Build the field and the motion with references/noise-and-fields.md — noise, fbm, domain warping, curl. Most beautiful motion is a field being sampled.
- Decide CPU or GPU early with references/gpu-and-shaders.md. This is architectural, not an optimisation — some systems simply do not express themselves below a population the CPU cannot reach, and porting later means rewriting.
- Render it well with references/rendering.md — trails via accumulation, additive blending, envelopes so nothing pops.
- Map the field to the screen with references/density-and-tone.md. Accumulation buffers are unbounded and displays are not; this mapping is where technically-correct pieces most often look wrong.
- Finish it with references/post-processing.md — bloom, grain, vignette, grading. The cheapest quality per line of code in the discipline.
- Art-direct it against references/art-direction.md — the checklist that separates a piece from a screensaver.
- Watch it. Record with
../motion/scripts/capture-motion.pyand look at the result over a long run, not one frame. Generative work fails slowly: it looks great at 4 seconds and turns to grey mush at 60. When something is wrong, work references/diagnostic.md rather than tuning at random.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/art-direction.md 3.6 KB
- references/density-and-tone.md 6.2 KB
- references/diagnostic.md 5.9 KB
- references/gpu-and-shaders.md 9.1 KB
- references/noise-and-fields.md 4.7 KB
- references/post-processing.md 6.1 KB
- references/rendering.md 4.2 KB
- references/systems.md 9.4 KB
- references/three-dimensional.md 6.5 KB
- validate/attractors.py 5.3 KB runs code
- validate/gray_scott.py 4.0 KB runs code
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 · 76 lines · 150 tokens per session scan A d3d5f660b32b
generative-motion is a skill published in the GitHub repository jangles-byte/atelier (2 stars, last pushed 1mo ago), licensed MIT. It adds 150 tokens to every session and 1,276 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
html-ppt-zhangzara-biennale-yellow
A curatorial deck for a contemporary art biennale — the thesis, the rooms, the works, and the visitor journey. Built as a decision-grade design craft deck for museum board, curators.
html-ppt-zhangzara-block-frame
Rescuing a messy startup deck into a board-grade system — the diagnosis, the page grammar, and the rebuilt proof pages. Built as a decision-grade design craft deck for founders, exec presenter.
html-ppt-zhangzara-blue-professional
OpenDesign's QBR for the executive committee: what moved, what stalled, and the resource reallocation ask. Built as a decision-grade corporate strategy deck for executive committee.
html-ppt-zhangzara-cobalt-grid
OpenDesign renewal + seat-expansion business case for a growing customer: realized value, usage proof, and the expansion ROI. Built as a decision-grade B2B sales deck for champion, finance approver.
html-ppt-zhangzara-creative-mode
A brand visual-identity system reveal for an outdoor label — logo, color, type, and the rules that keep it consistent. Built as a decision-grade design craft deck for brand team, client.
html-ppt-zhangzara-editorial-tri-tone
A type-and-color system for a culture magazine relaunch — the grid, the tri-tone palette, and the layout kit. Built as a decision-grade design craft deck for editorial & design team.