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-validatenpx skills add luminary19/atelier --skill forge-validategit clone --depth 1 https://github.com/luminary19/atelierWrote 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/luminary19/atelier/forge-validate)<a href="https://agentmods.dev/skills/luminary19/atelier/forge-validate"><img src="https://agentmods.dev/badge/skills/luminary19/atelier/forge-validate.svg" alt="Measured on agentmods" 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 | $0.00178 | $0.02869 |
| Opus 5 | $0.00089 | $0.01435 |
| Sonnet 5 | $0.00036 | $0.00574 |
| Haiku 4.5 | $0.00018 | $0.00287 |
Grade A, and why
forge-validate 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 4d 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/adversarial-escalation.md 7.3 KB
- references/gltf-validator-guide.md 8.0 KB
- references/mesh-checklist.md 12 KB
- references/mesh-repair.md 10.0 KB
- references/printability.md 11 KB
- references/render-qa-guide.md 10 KB
- scripts/detect_hook.py 3.1 KB runs code
- scripts/detect.py 8.7 KB runs code
- scripts/topology_audit.py 7.6 KB runs code
- scripts/validate.py 26 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.
- 4d ago First seen · 214 lines · 178 tokens per session scan A d27fc556c0f4
forge-validate is a skill published in the GitHub repository luminary19/atelier (2 stars, last pushed 2mo ago), with no licence file. It adds 178 tokens to every session and 2,869 once invoked, about $0.0009 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
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
Use when the user wants the visual/experiential design of a product done systematically — a design system, a screen, a landing page, or a visual identity — grounded in researched real-world prior art and free of AI slop. Establishes/extends the design system, invokes the matching local taste skill, dispatches the…
motion-system
Define motion tokens — durations, easing vocabulary, and reduced-motion handling — for consistency product-wide. Use when standardising motion across a system. For crafting one specific animation, use animation-principles (interaction-design).
icon-system
Specify an icon system — grid, sizing, stroke weight, naming, categories, and implementation. Use when standardising iconography. For broader illustration, use illustration-style (ui-design).
omd:media
Brand-consistent asset sets from DESIGN.md — hero, section illustrations, icon sets, OG image — generated through whichever channel the user actually has (grok build imagegen, Codex $imagegen, Gemini, xAI/Recraft/OpenAI keys) as recorded by omd:setup, with a provenance and cost ledger. No channel → prompt pack +…
omd:setup
Guided setup of the tools the design harness can use — image/video generation channels, browser, encoders. Detects what the user already has, explains pros/cons/costs, asks instead of instructing, and saves choices to .omd/config.json so every later design task reuses them. Trigger: 'omd setup', '도구 셋업', '이미지 생성 뭐 쓸 수…