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 alivirgo/Major-AI-Skills --skill zbrushgit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote 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/alivirgo/major-ai-skills/zbrush)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/zbrush"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/zbrush/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/alivirgo/major-ai-skills/zbrush"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/zbrush.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 | $0.00046 | $0.01672 |
| Opus 5.5 | $0.00018 | $0.00669 |
| Sonnet 5.5 | $0.00009 | $0.00334 |
| Haiku 4.5 | $0.00005 | $0.00167 |
Grade A, and why
zbrush 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 13d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maxon ZBrush AI Skill Guide (Claude)
Overview & Engine Architecture
Maxon ZBrush is a high-density sculpting DCC (often tens of millions of polygons). Agents should treat tools as SubTool hierarchies + SDiv levels, Dynamesh/Sculptris as topology regenerators, ZRemesher as a quad-flow contract, and Multi Map Exporter as a 32-bit displacement pipeline—not 8-bit previews. Automation is primarily ZScript (.txt / compiled .zsc), plus GoZ bridges to Maya/C4D/Blender.
┌─────────────────────────────────────────────────────────────┐
│ ZBrush sculpt → retopo → maps │
│ │
│ Geometry │
│ ├── SubTools + PolyGroups │
│ ├── SDiv multi-res / Dynamesh / Sculptris Pro │
│ └── ZRemesher + Decimation Master │
│ │
│ Pipeline │
│ ├── ZScript macros ([IFreeze] loops) │
│ ├── Multi Map Exporter (32-bit EXR displacement) │
│ └── GoZ interchange cache │
└─────────────────────────────────────────────────────────────┘
Version pins: document ZBrush year/build and plugin paths (ZStartup/ZPlugs64). UI path strings in ZScript break across versions—prefer documented plugin menu paths the studio actually ships.
When to use / when not to
Use when
- Organic/hard-surface sculpt, retopo via ZRemesher, decimation for game proxies.
- Extracting displacement/normal maps for downstream renderers.
- Batch SubTool export / GoZ handoff macros.
Do not use when
- Primary need is procedural FX sims →
@houdini. - Final PBR layer painting →
@substance-painterafter UVs. - Full scene lighting/ MoGraph →
@cinema-4d/@blender.
Operational Capabilities & Agent Directives
What ships with it
2 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.
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.
- 13d ago Changed · +40 lines · +14 tokens per session db497fc32951
- 1mo ago Changed · -15 tokens per session f838fe44ba72
- 2mo ago First seen · 117 lines · 47 tokens per session scan A adbfe6059a16
zbrush is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 1,672 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.
zbrush compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| zbrushalivirgo/Major-AI-Skills | Skill | 2 | yesterday | MIT | A | 46 | Claude Code |
| brand-assets-setupJohnWayneeee/ai-agent-skills | Skill | 1 | 13d ago | MIT | A | 41 | Claude Code |
| browser-auditJohnWayneeee/ai-agent-skills | Skill | 1 | 13d ago | MIT | A | 96 | Codex |
| workflow-node-setupJohnWayneeee/ai-agent-skills | Skill | 1 | 13d ago | MIT | A | 59 | Codex |
| payoff-action-modelingJohnWayneeee/ai-agent-skills | Skill | 1 | 13d ago | MIT | A | 86 | Codex |
| ui-final-polishJohnWayneeee/ai-agent-skills | Skill | 1 | 13d ago | MIT | A | 75 | Claude Code, Codex |
| figma-pencil-fsd-tailwind4JohnWayneeee/ai-agent-skills | Skill | 1 | 13d ago | MIT | A | 79 | Claude Code, Codex |