use-skills

use-skills is a cursor rule for Cursor from punkadillo/figma-code-composer. It costs 436 tokens per session, scanned A, original, MIT.

Rules that tell Cursor agents where to find and how to read skills for a Figma design-to-code pipeline. Cursor is a code editor with AI agents, and these rules point those agents to project-local instruction files.

In plain words
What is it for?
Use them when Cursor agents need to locate, load, and follow a specific Figma-pipeline skill.
Why use it?
They give agents a consistent way to load the right instructions and explain what to do if a skill file is missing. The rules are generated by the pipeline setup and may be overwritten or removed by it.

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/punkadillo/figma-code-composer/use-skills
Clone the repo
git clone --depth 1 https://github.com/punkadillo/figma-code-composer

Made for: Cursor.

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 use-skills

README.md
[![agentmods](https://agentmods.dev/badge/rules/punkadillo/figma-code-composer/use-skills.svg)](https://agentmods.dev/rules/punkadillo/figma-code-composer/use-skills)
Your own site
<a href="https://agentmods.dev/rules/punkadillo/figma-code-composer/use-skills"><img src="https://agentmods.dev/badge/rules/punkadillo/figma-code-composer/use-skills.svg" alt="Measured on agentmods" height="20"></a>
Per session 436 This file is loaded in full into every session.
When invoked 436 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00436 $0.00436
Opus 5 $0.00218 $0.00218
Sonnet 5 $0.00087 $0.00087
Haiku 4.5 $0.00044 $0.00044

Measured 3d ago against content hash 36e9e779cb08, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

use-skills 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 3d 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.

.cursor/rules/use-skills.mdc · 31 lines

What it actually says

Using figma-pipeline skills from Cursor

Cursor does not have a native skill loader. The figma-to-code orchestration pipeline ships a curated skill catalog at:

.figma-pipeline/skills/<skill-name>/SKILL.md

When an agent prompt (in .cursor/prompts/<agent>.md) tells you to "load skill X" or "invoke skill X", do the following:

  1. Open .figma-pipeline/skills/<X>/SKILL.md via @.figma-pipeline/skills/<X>/SKILL.md (or read it directly).
  2. Treat its content as authoritative guidance for the rest of the current run.
  3. If the SKILL.md references companion files (e.g. references/*.md, assets/*), read those too as needed.
  4. If the skill directory is missing, record it in your run's flags[] and proceed without it — never block.

Resolution

Which skills apply to the current run is computed by .figma-pipeline/protocols/skills.md § Resolution algorithm, based on .figma-pipeline/config.json (framework, CSS system, design system OR methodology, stories, unit tests, E2E). The wizard's install phase already pruned .figma-pipeline/skills/ down to the resolved set, so anything still on disk is meant to be loaded — agents don't need to re-derive applicability.

Do NOT

  • Do not write into .figma-pipeline/skills/<name>/ — the wizard owns that directory.
  • Do not look in .claude/skills/ from Cursor; those are Claude-Code-only symlinks. The canonical location is .figma-pipeline/skills/.
  • Do not invent skill names that don't exist on disk.
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. 3d ago First seen · 31 lines · 436 tokens per session scan A 36e9e779cb08

Subscribe to this mod's changes

use-skills is a cursor rule published in the GitHub repository punkadillo/figma-code-composer (3 stars, last pushed 15d ago), licensed MIT. It adds 436 tokens to every session, about $0.0022 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.