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 atezer/FMCP --skill design-token-pipelinegit clone --depth 1 https://github.com/atezer/FMCPWrote 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/atezer/fmcp/design-token-pipeline)<a href="https://agentmods.dev/skills/atezer/fmcp/design-token-pipeline"><img src="https://agentmods.dev/badge/skills/atezer/fmcp/design-token-pipeline/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/atezer/fmcp/design-token-pipeline"><img src="https://agentmods.dev/badge/skills/atezer/fmcp/design-token-pipeline.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 | $0.00149 | $0.06243 |
| Opus 5.5 | $0.00060 | $0.02497 |
| Sonnet 5.5 | $0.00030 | $0.01249 |
| Haiku 4.5 | $0.00015 | $0.00624 |
Grade A, and why
design-token-pipeline 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.
How it starts
The opening of the file, as written. The whole thing — 664 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Token Pipeline (Multi-Platform)
Design Token Kuralı: Bu skill'deki kod örneklerinde geçen font adları, renk kodları, piksel boyutları yalnızca FORMAT gösterimidir. Çalışma anında tüm design token değerleri (font, renk, boyut, spacing, radius, gölge) kayıtlı kütüphaneden (
figma_get_variables,figma_get_styles) veya kullanıcıdan okunmalıdır. Hardcoded token değeri kullanma. Detay:project-context.md→ "Design Token Kuralı".
Overview
Bu skill, Figma'daki design token'ları (variable'lar ve style'lar) iOS, Android ve Web platformlarının kullandığı formatlarda kod dosyalarına dönüştürür. Resmi Figma plugininde bu özellik yoktur.
Önemli: MCP araçları (figma_get_variables, figma_get_styles, figma_get_token_browser) ham variable ve style verisi döner. Platform-spesifik dosya formatlarına dönüşüm (Swift, XML, CSS vb.) AI agent tarafından yapılır. Araçlar doğrudan Swift/XML/CSS export etmez.
Desteklenen çıktı formatları:
| Platform | Format | Dosya |
|---|---|---|
| iOS | Swift Color extension | Colors.swift |
| iOS | Swift Font extension | Typography.swift |
| iOS | Swift Spacing constants | Spacing.swift |
| iOS | Asset Catalog color set | *.colorset/Contents.json |
| Android | XML resources | colors.xml, dimens.xml, styles.xml |
| Android | Compose Color object | AppColors.kt |
| Android | Compose Typography | AppTypography.kt |
| Android | Compose Spacing | AppSpacing.kt |
| Web | CSS Custom Properties | tokens.css |
| Web | Tailwind config | tailwind.config.js |
| Web | TypeScript constants | tokens.ts |
| Web | Sass variables | _tokens.scss |
| JSON | W3C Design Tokens | tokens.json |
Ek özellikler:
- Mode desteği (Light/Dark tema — variable'ların
valuesByModealanından) - Alias zinciri çözümleme (variable referansları
type: "VARIABLE_ALIAS"olarak gelir, AI takip eder) - Incremental güncelleme (mevcut dosyalar okunup, sadece değişenler güncellenir)
- Kategori bazlı export
- Cross-platform token değeri tutarlılık doğrulaması
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 · 664 lines · 149 tokens per session scan A 1378c021c579
design-token-pipeline is a skill published in the GitHub repository atezer/FMCP (10 stars, last pushed 22d ago), licensed MIT. It adds 149 tokens to every session and 6,243 once invoked, about $0.0006 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-token-pipeline compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| design-token-pipelineatezer/FMCP | Skill | 10 | 22d ago | MIT | A | 149 | Claude Code |
| token-auditmurphytrueman/design-system-ops | Skill | 215 | 1mo ago | MIT | A | 72 | Claude Code |
| accessibility-per-componentmurphytrueman/design-system-ops | Skill | 215 | 1mo ago | MIT | A | 68 | Claude Code |
| component-decision-treemurphytrueman/design-system-ops | Skill | 215 | 1mo ago | MIT | A | 65 | Claude Code |
| figma-variable-auditmurphytrueman/design-system-ops | Skill | 215 | 1mo ago | MIT | A | 63 | Claude Code |
| metadata-schema-generatormurphytrueman/design-system-ops | Skill | 215 | 1mo ago | MIT | A | 62 | Claude Code |
| theme-auditmurphytrueman/design-system-ops | Skill | 215 | 1mo ago | MIT | A | 57 | Claude Code |