figma-handoff

figma-handoff is a skill for Claude Code, Codex from m-binimran/design-pack. It costs 50 tokens per session (326 once invoked), scanned A, original, MIT.

A Figma-to-developer handoff process that turns a Figma design into implementation notes. Figma is a collaborative design tool used to plan screens, components, styles, and assets.

In plain words
What is it for?
Use it to extract design tokens, screen specifications, interaction states, exportable assets, component notes, and an issues list from a Figma file.
Why use it?
It gives developers measured design details and identifies missing states or visual problems without guessing values.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to extract design tokens, screen specifications, interaction states, exportable assets, component notes, and an issues list from a Figma file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/m-binimran/design-pack/figma-handoff
Install

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.

Any agent
npx skills add m-binimran/design-pack --skill figma-handoff
Clone the repo
git clone --depth 1 https://github.com/m-binimran/design-pack

Made for: Claude Code, Codex.

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 figma-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/m-binimran/design-pack/figma-handoff/github.svg)](https://agentmods.dev/skills/m-binimran/design-pack/figma-handoff)
Your own site
<a href="https://agentmods.dev/skills/m-binimran/design-pack/figma-handoff"><img src="https://agentmods.dev/badge/skills/m-binimran/design-pack/figma-handoff/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 figma-handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/m-binimran/design-pack/figma-handoff"><img src="https://agentmods.dev/badge/skills/m-binimran/design-pack/figma-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 326 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00050 $0.00326
Opus 5 $0.00025 $0.00163
Sonnet 5 $0.00010 $0.00065
Haiku 4.5 $0.00005 $0.00033

Measured 9d ago against content hash 63272885d4cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

figma-handoff 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 9d 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.

skills/figma-handoff/SKILL.md · 27 lines

What it actually says

figma-handoff

Turn a Figma file into a clean, accurate handoff using the Figma connector (never guess values).

Process

  1. Read the design via Figma: frames, variables/tokens, text styles, components, screenshots. If Figma isn't connected, say so - don't invent frame names or values.
  2. Extract tokens (hand to design-tokens): colours, type scale, spacing, radius, shadows - from Figma variables, not eyeballed.
  3. Spec the screens: spacing, sizes, breakpoints, states (hover/active/disabled/empty/error), interactions.
  4. List assets to export with names + formats + densities (hand to asset-export).
  5. Flag issues: contrast misses (the contrast-guard hook + accessibility-contrast), inconsistent spacing/type, missing states.

Output

  • A handoff doc: tokens, per-screen specs, asset export list, component notes, and an issues list. Every value sourced from Figma or marked [verify].

Guardrails

  • All measurements come from the Figma connector or are flagged - no fabricated pixels.
  • Don't claim a file was read if the connector didn't return it.
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. 9d ago First seen · 27 lines · 50 tokens per session scan A 63272885d4cd

Subscribe to this mod's changes

figma-handoff is a skill published in the GitHub repository m-binimran/design-pack (4 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 326 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

canva-mcp

Design MCP server by Canva.

Friz-zy/ai-capability-registry · 11 tokens

canva-brand-kit

Manage and apply brand kits in Canva. Use this skill when user wants to work with brand colors, fonts, logos, or maintain brand consistency across designs. Helps define brand guidelines and ensures designs follow brand standards. Requires Canva Pro/Enterprise for full brand kit features.

OpenAnalystInc/10x-Content-Expert · 60 tokens

canva-design-terminology

Design knowledge base for understanding design terminology, concepts, and best practices. Use this skill when user asks about design terms, needs guidance on design principles, or wants to understand Canva-specific features. Provides educational information, not direct Canva operations. Reference skill for other…

OpenAnalystInc/10x-Content-Expert · 62 tokens

canva-manager

Comprehensive Canva API integration skill for managing designs, folders, assets, and exports. Uses a 3-mode workflow: PLAN (analyze what needs to be done), CLARIFY (ask user questions), and IMPLEMENT (execute changes via Python scripts). Ensures safe operations by always confirming changes before execution. Use this…

OpenAnalystInc/10x-Content-Expert · 97 tokens

canva-image-editor

Edit and modify image-based designs in Canva (social media posts, posters, flyers, etc.). Use this skill when user wants to modify existing image designs or create new ones. Follows 3-mode workflow: PLAN changes, CLARIFY with user, then IMPLEMENT. For presentations use canva-presentation skill. For videos use…

OpenAnalystInc/10x-Content-Expert · 76 tokens

tldraw-canvas

Create interactive visual canvases using TLDraw React SDK. Generates mind maps, content plans, pipeline visualizations, and brainstorming boards.

OpenAnalystInc/10x-Content-Expert · 0 tokens