What is figma-agent-mcp AGENTS.md?

A set of instructions for AI coding agents working with Figma, a collaborative design tool. It explains how to use Figma tools and apply layout and design rules.

Creating and editing Figma designs, including frames, auto-layout structures, styles, and text.

It gives agents clear rules for making Figma changes consistently and with fewer unnecessary tool calls.

How TrungLee003/figma-agent-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to TrungLee003/figma-agent-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/TrungLee003/figma-agent-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/TrungLee003/figma-agent-mcp

Made for: Codex, 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/trunglee003/figma-agent-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/trunglee003/figma-agent-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/trunglee003/figma-agent-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/trunglee003/figma-agent-mcp/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/trunglee003/figma-agent-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/trunglee003/figma-agent-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 641 This file is loaded in full into every session.

When invoked 641 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00641	$0.00641
Opus 5.5	$0.00256	$0.00256
Sonnet 5.5	$0.00128	$0.00128
Haiku 4.5	$0.00064	$0.00064

Measured 2mo ago against content hash e2b20f39f903, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

figma-agent-mcp AGENTS.md 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 2mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

figma-agent-mcp GEMINI.md — 95% identical, 2 lines differ

AGENTS.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Figma Agent MCP Guidelines

This file provides rules and best practices for AI coding agents (Antigravity, Claude Code, Cursor, Copilot) when performing Figma design tasks.

🚀 Instant Single-Turn Execution (No Exploratory Latency)

NEVER search the filesystem for tool schemas:
- All 50 Figma MCP tools (figma.batch_execute, figma.create_frame, figma.run_skill, figma.resolve_design_system, etc.) are natively available.
- Do NOT run grep, find_by_name, or bash scripts looking for .ts schemas.
ALWAYS use figma.batch_execute for multi-node designs:
- Never make 20-30 sequential tool calls.
- Package all creation, auto-layout, styling, and text commands into 1 single atomic batch transaction using symbolic references (ref, parentRef, nodeRef, $ref:name).
ALWAYS enforce Auto Layout & Design Standards:
- Never use manual coordinates ($x, y$) for child elements.
- Use mode: "VERTICAL" or "HORIZONTAL", padding (16, 24), itemSpacing (8, 12, 16, 20, 24).
- Use layoutSizingHorizontal: "FILL" and layoutSizingVertical: "HUG" for responsive nesting.
- Modern palettes: #FFFFFF on #F8FAFC (subtle border 1px SOLID #E2E8F0) or #1E293B on #0F172A (border #334155), primary accent #6366F1 (Indigo).

🧩 Figma Agent Skills Catalog

The 9 Agent Workflow Skills are located in skills/, .agents/skills/, and .gemini/skills/:

inspect-design (skill.inspect_design): Deep inspect hierarchy, compact DSL, and WCAG contrast.
create-screen (skill.create_screen): Construct responsive full-screen frames (mobile, tablet, desktop, modal).
edit-selection (skill.edit_selection): Batch update styling, padding, gap, radius on active selection.
create-component (skill.create_component): Convert frame to reusable Master Component.
apply-design-system (skill.apply_design_system): Scan raw elements and bind Color Variables & Spacing Tokens.
validate-design (skill.validate_design): Design QA scoring (0-100), WCAG AA/AAA, Auto Layout compliance.
create-design-system (skill.create_design_system): Generate turnkey Color Tokens, Paint Styles, and Button Component.
auto-fix-accessibility (skill.auto_fix_accessibility): Automatically repair text colors violating WCAG contrast.
convert-wireframe-to-hifi (skill.convert_wireframe_to_hifi): Upgrade wireframe boxes to modern polished UI Cards.

Read the full file on GitHub · 34 lines

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.

2mo ago First seen · 34 lines · 641 tokens per session scan A e2b20f39f903

Subscribe to this mod's changes

figma-agent-mcp AGENTS.md is an instructions file published in the GitHub repository TrungLee003/figma-agent-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 641 tokens to every session, about $0.0026 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 2026-08-31.

Design and UX

figma-agent-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
figma-agent-mcp AGENTS.mdTrungLee003/figma-agent-mcp	Instructions file	1	2mo ago	MIT	A	641	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

figma-agent-mcp: Instructions file for Codex