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.
npx agentmods add rules/punkadillo/figma-code-composer/use-skillsgit clone --depth 1 https://github.com/punkadillo/figma-code-composerWrote 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.
[](https://agentmods.dev/rules/punkadillo/figma-code-composer/use-skills)<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>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 | $0.00436 | $0.00436 |
| Opus 5 | $0.00218 | $0.00218 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
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.
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:
- Open
.figma-pipeline/skills/<X>/SKILL.mdvia@.figma-pipeline/skills/<X>/SKILL.md(or read it directly). - Treat its content as authoritative guidance for the rest of the current run.
- If the SKILL.md references companion files (e.g.
references/*.md,assets/*), read those too as needed. - 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.
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.
- 3d ago First seen · 31 lines · 436 tokens per session scan A 36e9e779cb08
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.
Other cursor rules, from other repositories
ui-ux-godmode
A Curated AI AGENT OS – Optimized agent skills and add-ons like memB, OpenWiki, Heimdall Token Saver, and Godmode architectures.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.