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-fluid-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-fluid-scenes)<a href="https://agentmods.dev/skills/wkzmagician/newton-mcp/design-fluid-scenes"><img src="https://agentmods.dev/badge/skills/wkzmagician/newton-mcp/design-fluid-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-fluid-scenes"><img src="https://agentmods.dev/badge/skills/wkzmagician/newton-mcp/design-fluid-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 | $0.00056 | $0.00380 |
| Opus 5.5 | $0.00022 | $0.00152 |
| Sonnet 5.5 | $0.00011 | $0.00076 |
| Haiku 4.5 | $0.00006 | $0.00038 |
Grade A, and why
design-fluid-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 fluid scenes
- Choose
phase: smokefor a MAC-grid gas orphase: liquidfor APIC/FLIP particles. - Represent liquid initial volume with
sizeandparticle_spacing[m]; describe smoke sources with timedemitters. - Use
motion: staticrigid bodies orcontainerobjects for floors, walls, and obstacles. - Leave clearance of at least one particle spacing between fluid particles and container boundaries; use more clearance for fast rigid impacts.
- Use
solver: auto; smoke routes tosmokeand liquid routes toapic. - Use uniform or radial fields for wind, attraction, repulsion, and other bulk effects.
- Estimate initial particles as
volume / spacing^3; add emitter cross-section samples multiplied by active simulation substeps. For APIC adaptive resampling, also reserve roughly five particles per liquid grid cell. Capacity must cover the largest of these estimates. - Prefer a short low-resolution validation run before a final render.
Specify liquid density, viscosity, surface tension, and flip_ratio, or smoke buoyancy and dissipation, directly in the scene IR.
Start smoke at 20--30 FPS and liquid at 20--25 FPS. Higher FLIP ratios preserve splash energy but need more boundary clearance; viscosity damps motion; smaller spacing increases particle count cubically. For pressure_nonconvergence, fix clearance and spacing before raising iterations. For capacity failures, increase spacing or shorten/narrow emission rather than continually raising capacity.
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 · 20 lines · 56 tokens per session scan A ca433cbed0c5
design-fluid-scenes is a skill published in the GitHub repository wkzMagician/newton-mcp (0 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 380 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-fluid-scenes compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| design-fluid-sceneswkzMagician/newton-mcp | Skill | 0 | 3mo ago | Apache-2.0 | A | 56 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | yesterday | Apache-2.0 | A | 123 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 44 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 83 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | today | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | today | Apache-2.0 | A | 205 | Claude Code |