mcp-figma

mcp-figma is a skill for Claude Code, OpenCode from MichelKerkmeester/skilled-agent-harness_spec-driven-loops. It costs 35 tokens per session (7,674 once invoked), scanned C, original, MIT.

A command-line connector for working with Figma, a collaborative interface-design tool. It can read, create, modify, and export designs, design tokens, and components, with optional Figma MCP support.

In plain words
What is it for?
Use it to inspect or update Figma designs, tokens, components, and exports.
Why use it?
It lets a coding agent coordinate design files and implementation details from the terminal.

Skill for Claude CodeOpenCode

Written for Claude Code and OpenCode: allowed-tools in frontmatter, but also installed under .opencode/. Also seen: mentions AGENTS.md.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Resilience pattern: see [sk-doc smart-router template](../../sk-doc/sk-create-skill/assets/skill/skill-smart-router.md). Guard paths, discover at runtime, score.

Good fit Use it to inspect or update Figma designs, tokens, components, and exports.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loops
agentmods
npx agentmods add skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-figma

Made for: Claude Code, OpenCode.

Wrote 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.

agentmods badge for mcp-figma

README.md
[![agentmods](https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-figma/github.svg)](https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-figma)
Your own site
<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-figma"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-figma/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.

agentmods 80×15 button for mcp-figma

Your own site · 80×15
<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-figma"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/mcp-figma.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,674 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.07674
Opus 5 $0.00017 $0.03837
Sonnet 5 $0.00007 $0.01535
Haiku 4.5 $0.00003 $0.00767

Measured yesterday against content hash 9b535401d41a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

mcp-figma scanned grade C with 1 finding 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 yesterday.

The scan reads SKILL.md. This mod also ships 11 executable files (examples/inspect-export-readonly.sh, examples/safe-connect-daemon-health.sh, mcp-servers/figma-cli/setup.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- Keywords: figma, figma-cli, figma-ds-cli, figma-desktop, design-tokens, variables, components, render-jsx, figma-export, design-system, figma-daemon, figma-mcp, figma-developer-mcp, code-mode -->
.opencode/skills/mcp-tooling/mcp-figma/SKILL.md · 377 lines

How it starts

The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Figma (mcp-figma)

Drive Figma Desktop from the terminal through the silships figma-cli (published as figma-ds-cli) so a coding agent can read, author, modify, and export designs, tokens, and components, and optionally pull design context out of Figma through a Figma MCP via Code Mode. The CLI is the primary surface. The MCP is opt-in. Deep operational detail lives in references/figma-cli-reference.md.

Naming trap (read first). The silships tool publishes to npm as figma-ds-cli (the unambiguous binary). The npm package literally named figma-cli is an UNRELATED tool (unic/figma-cli, bin figma), so never npm i -g figma-cli. The figma-cli command only exists when installed from the silships repo (main, exposes both figma-ds-cli and figma-cli). This skill uses figma-ds-cli as the canonical command throughout.

Version trap. npm publishes only [email protected], a minimal build with no --safe, no daemon, no extract and ~12 commands. The full surface this skill documents (safe connect, daemon, extract/import, ~130 commands) is 1.2.0, available only from the silships repo. Install via scripts/install.sh (--source repo, or --source auto which upgrades when npm is stale), then confirm figma-ds-cli --version is >= 1.2.0.


1. WHEN TO USE

Activation Triggers

Use when the user wants to:

  • Drive Figma Desktop from the terminal: create/render frames, components, icons, layouts, or images.
  • Work a design system in Figma: tokens, variables, collections, var:name binding, shadcn primitives.
  • Inspect or export from Figma: extract to DESIGN.md, export PNG/SVG/JSX/CSS/Tailwind/Storybook, screenshots, a11y audits.
  • Import a design system INTO Figma: from Tailwind config, CSS variables, tokens.json, or Storybook.
  • Set up or troubleshoot the figma-cli connection or daemon (safe plugin vs yolo patch, daemon health).
  • Optionally pull design context FROM Figma into the agent via a Figma MCP (Framelink figma) through Code Mode.

Read the full file on GitHub · 377 lines

Files

What ships with it

54 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.

Changes

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.

  1. yesterday Changed 9b535401d41a
  2. 7d ago First seen · 377 lines · 35 tokens per session scan C 7b6d85ca21fc

Subscribe to this mod's changes

mcp-figma is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 7,674 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

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.

nexu-io/open-design · 41 tokens

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.

nexu-io/open-design · 53 tokens

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).

nexu-io/open-design · 78 tokens

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.

Yeachan-Heo/oh-my-codex · 50 tokens

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.

microsoft/hve-core · 47 tokens

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.

Hisn00w/ASu-skills · 86 tokens