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 skills add wkzMagician/newton-mcp --skill design-cloth-scenesgit clone --depth 1 https://github.com/wkzMagician/newton-mcpWrote 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/skills/wkzmagician/newton-mcp/design-cloth-scenes)<a href="https://agentmods.dev/skills/wkzmagician/newton-mcp/design-cloth-scenes"><img src="https://agentmods.dev/badge/skills/wkzmagician/newton-mcp/design-cloth-scenes/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/skills/wkzmagician/newton-mcp/design-cloth-scenes"><img src="https://agentmods.dev/badge/skills/wkzmagician/newton-mcp/design-cloth-scenes.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 | $0.00050 | $0.00455 |
| Opus 5.5 | $0.00020 | $0.00182 |
| Sonnet 5.5 | $0.00010 | $0.00091 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
design-cloth-scenes 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 2mo 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.
What it actually says
Design cloth scenes
- Represent each thin deformable sheet as a
clothobject with physical size in meters. - Choose resolution from the visible deformation scale; begin around 11--16 vertices per axis. Treat 24 per axis as a preview ceiling, not a default target.
- Keep particle spacing approximately uniform in both axes.
- Use
fixed-pointconstraints for pins, hooks, curtain rails, and flag attachments. - Use rigid objects as colliders rather than encoding collision behavior as constraints.
- Prefer
solver: autoorsolver: vbdfor cloth. Use XPBD only when a tested interaction specifically requires it. - Start surface density in the low single-digit kg/m2 range. Very low surface density makes ordinary forces and impacts disproportionately violent.
- Set area stiffness alongside stretch stiffness; begin with comparable values. Use bend stiffness at least one to two orders below in-plane stiffness.
- Use material damping in the low single digits as a stable starting range. Values far below one provide little control for impacts or hanging motion.
- Tune in this order: geometry and clearance, surface density, paired area/stretch stiffness, damping, substeps, solver iterations, then resolution. Change only one category per repair.
- Treat thickness as collision thickness [m], not visual fabric thickness alone.
Verify that fixed points correspond to cloth vertices when compiling to Newton. Avoid over-constraining the same region with contradictory anchors.
Never increase resolution, substeps, and solver iterations together. Avoid enabling self-collision unless the requested folds require it because it adds contact work and can amplify unstable material choices. For cloth_deformation_failure, first reduce impact or forcing, then improve surface density, paired area/stretch stiffness, and damping; for energy_explosion, remove extreme forces and stiffness before adding substeps. Explicit vertex-index pins depend on topology, while edge and UV-corner selectors remain meaningful after safe preview downsampling.
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.
- 2mo ago First seen · 23 lines · 50 tokens per session scan A 49d86ba44daf
design-cloth-scenes is a skill published in the GitHub repository wkzMagician/newton-mcp (0 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 455 once invoked, about $0.0002 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.
design-cloth-scenes compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| design-cloth-sceneswkzMagician/newton-mcp | Skill | 0 | 3mo ago | Apache-2.0 | A | 50 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 5d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |