Borrowing it
Nothing to install: this file belongs to satanyakiv/NutriSport. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/satanyakiv/NutriSport/main/.claude/skills/figma-mcp-budget/SKILL.mdgit clone --depth 1 https://github.com/satanyakiv/NutriSportWrote 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/satanyakiv/nutrisport/figma-mcp-budget)<a href="https://agentmods.dev/skills/satanyakiv/nutrisport/figma-mcp-budget"><img src="https://agentmods.dev/badge/skills/satanyakiv/nutrisport/figma-mcp-budget/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/satanyakiv/nutrisport/figma-mcp-budget"><img src="https://agentmods.dev/badge/skills/satanyakiv/nutrisport/figma-mcp-budget.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 | $0.00156 | $0.01399 |
| Opus 5 | $0.00078 | $0.00700 |
| Sonnet 5 | $0.00031 | $0.00280 |
| Haiku 4.5 | $0.00016 | $0.00140 |
Grade A, and why
figma-mcp-budget 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 12d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma MCP Budget — discipline rules
Context
Figma Pro plan ($20/month) caps: 10 calls/min (rolling 60s) and 200 calls/day (UTC rollover). Personal-account caps; team plan does not help. One runaway loop on a missing nodeId burns the daily budget in 5 minutes — see references/failure-modes.md. This skill is orthogonal to figma-handoff: handoff defines WHAT to call, this defines HOW to call safely.
When to activate
- Before any series of ≥3 Figma MCP calls in a turn
- Before bootstrap operations (e.g. enumerating pages of a Figma file)
- At the start of
featurePhase A.1 (regardless ofscreens[]count) - When user says "Figma бюджет вичерпано" / "rate limit hit" / "429"
- Whenever you load
figma-handoff(it cross-references this skill in Step 0)
Rules (core, inline)
1. Prefer get_design_context for scope-bound nodes
get_design_context(fileKey, nodeId) returns code + screenshot + metadata in one call — cheaper than separate get_screenshot + get_metadata + get_variable_defs chain. Use when you have a specific nodeId.
2. get_metadata only as fallback
Use get_metadata ONLY when (a) get_design_context returned a truncation error and you need to drill into children, or (b) you're enumerating a known file as part of a one-time bootstrap (with hard cap, see references/extended-rules.md §10). Don't use it for exploration ("let me see what's in this page") — it times out on large pages and is wasteful when get_design_context would do.
3. Always pass nodeId
Never call get_design_context(fileKey) or get_metadata(fileKey) without a nodeId. Only exception: bootstrap pass against per-page nodeIds collected from a saved tree (e.g. .claude/figma/SCREEN_FRAME_MAP.md Phase 1 dump).
4. whoami once per session
whoami is exempt from rate limit — call it once per session for seat-type verification (Pro vs Org) and to confirm authenticated user. Do not re-call within the same conversation.
What ships with it
3 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.
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.
- 12d ago First seen · 81 lines · 0 tokens per session scan A d5c03f9e79c6
figma-mcp-budget is a skill published in the GitHub repository satanyakiv/NutriSport (11 stars, last pushed 3mo ago), licensed MIT. It adds 156 tokens to every session and 1,399 once invoked, about $0.0008 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 $ultragoal 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.