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 skills add yummylabs-coder/yummy-design-plugins --skill figma-component-docsgit clone --depth 1 https://github.com/yummylabs-coder/yummy-design-pluginsWrote 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/skills/yummylabs-coder/yummy-design-plugins/figma-component-docs)<a href="https://agentmods.dev/skills/yummylabs-coder/yummy-design-plugins/figma-component-docs"><img src="https://agentmods.dev/badge/skills/yummylabs-coder/yummy-design-plugins/figma-component-docs/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.
<a href="https://agentmods.dev/skills/yummylabs-coder/yummy-design-plugins/figma-component-docs"><img src="https://agentmods.dev/badge/skills/yummylabs-coder/yummy-design-plugins/figma-component-docs.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00177 | $0.02677 |
| Opus 5.5 | $0.00071 | $0.01071 |
| Sonnet 5.5 | $0.00035 | $0.00535 |
| Haiku 4.5 | $0.00018 | $0.00268 |
Grade A, and why
figma-component-docs 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 22d 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.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documenting a component in Figma
The format lives in references/doc-template.md. Read it first. It holds the block
order, the text limits, which blocks each component type gets, and the interaction
contract. This file is the procedure and the traps. It deliberately does not repeat the
limits, because two copies drift.
Three readers, one home each
Most component docs fail because one artifact is trying to serve three readers. Split them and each one gets better.
- The component description field is read by developers and their AI coding agents (Claude Code, Cursor, anything reading the file through an MCP). It decides how the component gets built and used, so it is dense and directive and can be long. When the description and the canvas disagree, the description wins, because it is the half that ships.
- The doc frame on the canvas is read by a person skimming. Short captions, real component instances carrying the meaning, and hard limits on how much text goes where.
- A decisions log (a markdown file in the repo, a Notion page, anything outside the canvas) holds history: what changed, when, and why. History never goes on the canvas.
Write the description and the frame. They are different artifacts and neither substitutes for the other.
Running code in Figma
Every script in scripts/ is plugin code, not a Node script. Run it through whichever
Figma MCP is connected:
- Figma Console MCP:
figma_execute, with the Desktop Bridge plugin running. - Official Figma MCP:
use_figma. Load itsfigma-useskill first if it has one.
Read the script, replace the placeholder constants at the top, and pass the whole file
as the code. Both scripts return a result object.
First time in a file: build the template
If the file has no doc/_Template frame, build it once:
- Ask the user which page holds components. Navigate there.
- Run
scripts/build-template.js. It creates a_Doc Templatesection holdingdoc/_Template, with every block, placeholder text and dashed specimen slot. - Run
scripts/verify.jsagainst the new template (see "The checker"). It must fail, with a violation for every placeholder. If the template ever comes back clean, the checker is broken, so stop and fix that before documenting anything. - Tell the user they can restyle the template (fonts, colors, their own text styles and variables) as long as they keep the layer names. The checker finds everything by name, so renaming a layer breaks it silently.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 22d ago First seen · 198 lines · 177 tokens per session scan A bb6a0a647469
figma-component-docs is a skill published in the GitHub repository yummylabs-coder/yummy-design-plugins (24 stars, last pushed 22d ago), licensed MIT. It adds 177 tokens to every session and 2,677 once invoked, about $0.0007 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 2026-09-29.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.