figma-design-to-code

figma-design-to-code is a command for Claude Code from Ghosteken/agent-harness. It costs 18 tokens per session (36 once invoked), scanned A, original, MIT.

A command for turning a Figma frame, file, or selection into production code that matches the design closely. Figma is a collaborative interface-design tool; the command also checks design data, assets, components, and the rendered result.

In plain words
What is it for?
Use it to implement a specific Figma screen or selection in the project's existing technology, reuse its components and design tokens, export exact assets, and compare the finished result with the Figma screenshot.
Why use it?
It reduces the mismatch between a design mock-up and the implemented screen. It also prevents common substitutions, such as replacing exact icons or images with hand-made or placeholder versions.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Part of the agent-harness plugin — 173 skills, 17 commands, 12 agents shipped together

Good fit Use it to implement a specific Figma screen or selection in the project's existing technology, reuse its components and design tokens, export exact assets, and compare the finished result with the Figma screenshot.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ghosteken/agent-harness/figma-design-to-code
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.

Clone the repo
git clone --depth 1 https://github.com/Ghosteken/agent-harness

Made for: Claude Code.

Or install agent-harness, the plugin that ships this one along with the rest of its 173 skills, 17 commands, 12 agents.

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-design-to-code

README.md
[![agentmods](https://agentmods.dev/badge/commands/ghosteken/agent-harness/figma-design-to-code/github.svg)](https://agentmods.dev/commands/ghosteken/agent-harness/figma-design-to-code)
Your own site
<a href="https://agentmods.dev/commands/ghosteken/agent-harness/figma-design-to-code"><img src="https://agentmods.dev/badge/commands/ghosteken/agent-harness/figma-design-to-code/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-design-to-code

Your own site · 80×15
<a href="https://agentmods.dev/commands/ghosteken/agent-harness/figma-design-to-code"><img src="https://agentmods.dev/badge/commands/ghosteken/agent-harness/figma-design-to-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 36 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 $0.00018 $0.00036
Opus 5.5 $0.00007 $0.00014
Sonnet 5.5 $0.00004 $0.00007
Haiku 4.5 $0.00002 $0.00004

Measured 23d ago against content hash 2b6364fa2fc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

figma-design-to-code 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 23d 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.

.claude/commands/figma-design-to-code.md · 6 lines

What it actually says

Invoke the agent-harness:figma-design-to-code skill.

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. 23d ago Changed · -4 lines 2b6364fa2fc7
  2. 1mo ago First seen · 10 lines · 18 tokens per session scan A 903c2cd5925a

Subscribe to this mod's changes

figma-design-to-code is a command published in the GitHub repository Ghosteken/agent-harness (4 stars, last pushed 6d ago), licensed MIT. It adds 18 tokens to every session and 36 once invoked, about $0.0001 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 2026-09-12.