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 bacchus-labs/wrangler --skill figma-variables-generatorgit clone --depth 1 https://github.com/bacchus-labs/wranglerWrote 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/bacchus-labs/wrangler/figma-variables-generator)<a href="https://agentmods.dev/skills/bacchus-labs/wrangler/figma-variables-generator"><img src="https://agentmods.dev/badge/skills/bacchus-labs/wrangler/figma-variables-generator/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/bacchus-labs/wrangler/figma-variables-generator"><img src="https://agentmods.dev/badge/skills/bacchus-labs/wrangler/figma-variables-generator.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 | $0.00097 | $0.04866 |
| Opus 5 | $0.00048 | $0.02433 |
| Sonnet 5 | $0.00019 | $0.00973 |
| Haiku 4.5 | $0.00010 | $0.00487 |
Grade A, and why
figma-variables-generator 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 9d 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 — 648 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma Variables Generator
Generate properly formatted JSON files for creating Figma variable collections from text descriptions, existing design token data, or images showing design systems.
Core Capabilities
This skill helps designers create Figma variable collections by generating the JSON format required by Figma variable import/export plugins. The output can be directly imported into Figma using plugins like "Variables Import Export" or similar tools.
Supported Variable Types
Figma supports only 4 core variable types:
- Color (
$type: "color") - RGB hex values, rgba, or variable references - Number (
$type: "number") - Numeric values (spacing, sizes, radius, weights, etc.) - String (
$type: "string") - Text values (font families, names, etc.) - Boolean (
$type: "boolean") - True/false values
Important: Types like spacing, borderRadius, fontSize, fontWeight should use number type. Use semantic naming in your variable paths to indicate their purpose (e.g., spacing.xs, radius.md, fontSize.body)
Key Features
- Multiple Modes: Support for different modes (e.g., Light/Dark themes)
- Variable References: Use
{collection.subcategory.variableName}syntax to reference other variables - Code Syntax: Optional platform-specific naming conventions (WEB, iOS, ANDROID)
- Hierarchical Organization: Group variables into collections, categories, and subcategories
- Flexible Input: Accept design tokens from text, structured data, or images
Workflow
Step 0: Check for Existing JSON (For Updates or Reformatting)
CRITICAL: When the user asks to update, add to, or reformat an existing JSON file, you MUST:
- Read the existing file first - Use the Read tool to load the current JSON
- Preserve all naming exactly - Collection names, category names, subcategory names, and variable names must match EXACTLY
- Understand Figma's behavior: Figma uses names as unique identifiers:
- Same name = overwrites/updates the variable
- Different name = creates a new variable/collection/category
- Maintain hierarchy - Keep the exact same nesting structure
- Reorder for readability - If JSON is messy or poorly organized, reorder it following the guidelines in Step 2.5
What ships with it
2 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.
- 9d ago First seen · 648 lines · 97 tokens per session scan A aa1e336961f6
figma-variables-generator is a skill published in the GitHub repository bacchus-labs/wrangler (4 stars, last pushed 6mo ago), licensed MIT. It adds 97 tokens to every session and 4,866 once invoked, about $0.0005 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 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 $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.