figma-environment-setup

A setup guide for creating a local design-system workspace and linking Cursor, a coding tool, to Figma, a collaborative design app. It prepares the connection needed to work with Figma variables, styles, and components.

In plain words
What is it for?
Use it when starting a design system, creating its project folder and settings file, or connecting Cursor to a Figma file.
Why use it?
It removes the initial setup work and checks that the local project and Figma connection are ready before other design-system tasks begin.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/jrpease/throughline/figma-environment-setup
Clone the repo
git clone --depth 1 https://github.com/jrpease/throughline

Made for: Cursor.

Per session 133 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,467 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00133 $0.05467
Opus 5 $0.00067 $0.02733
Sonnet 5 $0.00027 $0.01093
Haiku 4.5 $0.00013 $0.00547

Measured 2d ago against content hash 380d4d13ed2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

figma-environment-setup scanned grade B 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 2d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo chown -R $(whoami) ~/.npm
adapters/cursor/.cursor/rules/figma-environment-setup.mdc · 461 lines

How it starts

The opening of the file, as written. The whole thing — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Figma environment setup

This skill does three foundational jobs, in order:

  1. Discover where you're working — find or create the project directory, scan what's already there, and set expectations.
  2. Create the local working folder and write the design-system.json manifest into it (if not already present from step 1).
  3. Connect Cursor to Figma so later skills can read and write the file, then verify the connection works.

It is the required first step. Every other Figma skill does a cheap liveness check and, if it fails, points the user back here.

Who you're talking to

Assume the user is design-fluent but may have never set up a developer tool, created an API token, or used a terminal before. Explain every concept the first time it appears, in one plain sentence. Never assume they know what a "token", "MCP server", "config file", or "package manager" is. Be warm and concrete. When you ask them to do something outside the chat (in Figma, on a website), give the exact click path, not a vague instruction.

Read .throughline/references/manifest-schema.md before writing the manifest so you use the correct field names and defaults.

Step 0 — Intake (Locate → Scan → Brief)

This step runs before everything else. Establish where you're working, read what's already there, and set the user's expectations before taking any action. It has three phases in sequence.

Phase 1: Locate

Open by surfacing the user's current working directory and presenting three explicit options — no assumptions made about where they want to work or whether they have started anything already:

"Before we get started, I want to make sure we're working in the right place. You're currently in: [current working directory path]

Where should we set up?

  • Here — this directory is where the design system should live
  • Somewhere else — I have a project at a different path
  • A new folder — create a fresh folder somewhere"

"Here": Proceed to the existing manifest check below.

Read the full file on GitHub · 461 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.

  1. 2d ago First seen · 461 lines · 133 tokens per session scan B 380d4d13ed2d

Subscribe to this mod's changes

figma-environment-setup is a cursor rule published in the GitHub repository jrpease/throughline (76 stars, last pushed 4d ago), licensed MIT. It adds 133 tokens to every session and 5,467 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.