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/forgeyclap/claude-forge/forge-figmanpx skills add ForgeyClap/claude-forge --skill forge-figmagit clone --depth 1 https://github.com/ForgeyClap/claude-forgeWrote 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/forgeyclap/claude-forge/forge-figma)<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-figma"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-figma.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 | $0.00047 | $0.01167 |
| Opus 5 | $0.00023 | $0.00583 |
| Sonnet 5 | $0.00009 | $0.00233 |
| Haiku 4.5 | $0.00005 | $0.00117 |
Grade A, and why
forge-figma 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 5d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge playbook — Design → code (Figma / mockups)
ui-boss leads the translation under build-boss; a stack reviewer (react-reviewer or vue-reviewer) reviews the built components; a11y-architect guards accessibility. Design→code is website/frontend work, so the built result also runs under forge-website conventions (real content, responsive, a11y, no placeholders). The honesty rule here: state what you translated from — a live Figma read (MCP) or provided exports — and never invent measurements you couldn't see.
Hard rules (non-negotiable)
- Faithful translation, verified visually. Rendered output is compared side-by-side against the source frame at the design's breakpoints (spacing, sizing, hierarchy, states) — "close enough" from memory is not translation. Screenshot evidence, not assertion.
- Design tokens, not scattered magic values. Colours, typography, spacing, radii, shadows are extracted into tokens/variables (CSS custom properties, a tokens file, or a theme object) and reused — the design's real scale, not a fresh hardcoded hex/px per component.
- Responsive fidelity. The design's breakpoints are honoured (Figma usually ships desktop + mobile frames); layout adapts. No fixed-pixel-only layout that breaks off-frame.
- Accessibility is not optional. Semantic HTML, WCAG AA contrast, visible focus states, keyboard navigation, alt text, ARIA where needed. A design can look right and still fail contrast — flag the failure back, don't silently ship it. a11y wins over exact pixel-match.
- Component structure mirrors the design system. A Figma variant set (e.g. a
Buttonwith variants) becomes one prop-driven component, not copy-pasted one-offs. Real content from the design, no Lorem where real copy exists.
Team (conditional by stack/level)
Lead: ui-boss (design-led) or build-boss. Build review: react-reviewer or vue-reviewer (by stack). Accessibility: a11y-architect. Figma MCP wiring (opt-in): mcp-developer. Design critique of the translated result: the design-is skill. If it's a marketing/landing surface, seo-boss for meta/perf.
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.
- 5d ago First seen · 38 lines · 47 tokens per session scan A e968ae25e7c3
forge-figma is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 1,167 once invoked, about $0.0002 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
frame-flowchart-sticky
SVG 曲线连接 + 便利贴节点 + 光标交互, 像白板 brainstorm.
frame-liquid-bg-hero
WebGL 风流体置换背景 + 顶部叠加金句, 适合视频片头 / landing hero / 海报.
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.
saas-landing
单页 SaaS 落地页, 含 hero/features/social-proof/pricing/CTA.
waitlist-page
【模板: 等候名单页 / Waitlist】 【意图】为新产品 / 早鸟内测做一张极简等候页。 【布局】.
motion-frames
可循环 CSS 动效组合: 旋转环、地球仪、计时器、视差标签.