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 vladmdgolam/agent-skills --skill figma-context-mcpgit clone --depth 1 https://github.com/vladmdgolam/agent-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/vladmdgolam/agent-skills/figma-context-mcp)<a href="https://agentmods.dev/skills/vladmdgolam/agent-skills/figma-context-mcp"><img src="https://agentmods.dev/badge/skills/vladmdgolam/agent-skills/figma-context-mcp/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/vladmdgolam/agent-skills/figma-context-mcp"><img src="https://agentmods.dev/badge/skills/vladmdgolam/agent-skills/figma-context-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00138 | $0.01421 |
| Opus 5 | $0.00069 | $0.00711 |
| Sonnet 5 | $0.00028 | $0.00284 |
| Haiku 4.5 | $0.00014 | $0.00142 |
Grade A, and why
figma-context-mcp 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 11d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma Context MCP
Expert guide for the Figma Context MCP (also known as Framelink). Teaches efficient API usage patterns that prevent 429 rate-limit lockouts.
Tools
| Tool | Purpose | API Tier |
|---|---|---|
get_figma_data |
Fetch file/node structure, layout, components | Tier 1 (most restricted) |
download_figma_images |
Export PNG/SVG renders of specific nodes | Tier 2-3 |
Critical: Rate Limits
Figma enforces per-plan rate limits. Limits apply based on the file owner's plan, not yours:
| Tier | Starter | Pro | Org |
|---|---|---|---|
| Tier 1 (files) | 10/min | 15/min | 20/min |
| Tier 2 (images) | 25/min | 50/min | 100/min |
| Tier 3 | 50/min | 100/min | 150/min |
View/Collab seats get only 6 Tier-1 calls/month. If accessing files owned by someone on a Starter/free plan, their limits apply to you.
429 lockouts can last 4-5 days. Prevention is essential.
Workflow: Metadata-First Pipeline
Never fetch everything upfront. Adopt this pipeline to keep most jobs under 2-3 API calls and <500 KB:
1. Start with a targeted node, not the whole file
When a user provides a Figma URL like figma.com/design/FILEKEY/Name?node-id=123-456, always extract and pass the nodeId. Never fetch the entire file when a specific node is available.
get_figma_data(fileKey="ABC123", nodeId="123-456", depth=2)
2. Use minimal depth
Always set depth to limit tree traversal:
- depth=1: Top-level frame only (layout structure, component names)
- depth=2: Frame + direct children (usually sufficient for code generation)
- depth=3: Maximum recommended — only when nested auto-layouts require it
Default if omitted: the API returns the ENTIRE subtree — often megabytes for complex frames with 50-200+ children. This is the #1 cause of 429 errors.
3. Analyze locally before fetching more
After receiving the initial response:
- Identify which child nodes actually need detail (skip hidden, decorative, or library-referenced nodes)
- Extract design tokens (colors, spacing, typography) directly from the response — no extra calls needed
- Build your component structure from what you already have
What ships with it
1 file 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.
- 11d ago First seen · 123 lines · 138 tokens per session scan A 42483b8e2388
figma-context-mcp is a skill published in the GitHub repository vladmdgolam/agent-skills (8 stars, last pushed 3d ago), licensed MIT. It adds 138 tokens to every session and 1,421 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.