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/luminary19/atelier/forge-rendernpx skills add luminary19/atelier --skill forge-rendergit clone --depth 1 https://github.com/luminary19/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 | $0.00228 | $0.02628 |
| Opus 5 | $0.00114 | $0.01314 |
| Sonnet 5 | $0.00046 | $0.00526 |
| Haiku 4.5 | $0.00023 | $0.00263 |
Grade A, and why
forge-render 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 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.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
10 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/cli-invocations.md 11 KB
- references/contact-sheet.md 9.3 KB
- references/cycles-gpu-passes.md 19 KB
- references/workbench-diagnostic.md 15 KB
- scripts/__pycache__/contact_sheet.cpython-314.pyc 15 KB
- scripts/__pycache__/preflight.cpython-314.pyc 8.1 KB
- scripts/__pycache__/render.cpython-314.pyc 52 KB
- scripts/contact_sheet.py 12 KB runs code
- scripts/preflight.py 5.7 KB runs code
- scripts/render.py 38 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 · 207 lines · 228 tokens per session scan A d75aa9f46425
forge-render is a skill published in the GitHub repository luminary19/atelier (2 stars, last pushed 2mo ago), with no licence file. It adds 228 tokens to every session and 2,628 once invoked, about $0.0011 per session on Opus 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 skills, from other repositories
ban-pattern
Register AI-generated-looking UI patterns as prohibited rules in the design system. Use when user says "AIっぽい", "AI臭い", "これ禁止", "このパターンやめたい", "ban this pattern", "add to prohibited", or points out a generic/cookie-cutter UI element.
qiaomu-design
偏执型设计顾问 v3.7（融合版）— Jobs 式产品直觉 + Rams 式功能纯粹主义，融合多套顶级设计 Skill 实测精华 （Anthropic frontend-design 的美学胆量、Vercel web-design-guidelines 的工程规范、taste-skill 的反模板拨盘、 Emil Kowalski 的动效工艺、ui-ux-pro-max 的准则化组件行为、IBM Carbon 的组件/模式决策框架）。 重新设计页面、审视 UI 方案、优化交互体验、从零构建界面时使用。 触发词："重新设计"、"redesign"、"优化界面"、"优化交互"、"设计方案"、"UI 审查"、"这个页面不行"、…
morphous-catalog
Create or refresh Morphous website design-system/theme bundles from animal, insect, plant, landscape, mineral, weather, or other nature motifs. Use when Codex is asked to generate Morphous motif images, light/dark design-system boards, reusable image prompts, generated web assets, shadcn/tweakcn theme exports, or the…
design-review
HTMLファイルをmelta UIデザインシステムに照らしてレビューし、違反を検出・分類・修正提案する。トリガー: 「デザインレビュー」「DSチェック」「禁止パターンチェック」「design review」「check compliance」「DS準拠確認」。対象ファイルのパスを引数で受け取る。.
oil-frontend
用于实现、修改、重构或评审产品前端。当前任务涉及页面、组件、交互、表单、状态、数据流、Hook、类型、视觉层级、排版、颜色、圆角、阴影、图标、响应式、动效、改变可见结果的 CSS 或前端代码组织时自动触发。触发后先阅读 SKILL.md，按任务的主要决策只加载最小规则集。纯 CSS 语法、导入或类名修复且不改变界面结果时不触发；纯构建、部署、依赖升级、安全、后端任务，以及只解释前端概念而不处理项目实现的请求也不触发。.
balsa-ui
Build, fix, review, install, and validate Balsa UI open-code components for Vue applications. Use for focused Balsa repository maintenance, Vue UI built from Balsa components, compositions or blocks, semantic tokens, registry metadata, accessibility behavior, and installed-source update safety. Scale the workflow from…