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 SFKislev/Flue --skill figmagit clone --depth 1 https://github.com/SFKislev/FlueWrote 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/sfkislev/flue/figma)<a href="https://agentmods.dev/skills/sfkislev/flue/figma"><img src="https://agentmods.dev/badge/skills/sfkislev/flue/figma/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/sfkislev/flue/figma"><img src="https://agentmods.dev/badge/skills/sfkislev/flue/figma.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 | $0.00027 | $0.00505 |
| Opus 5.5 | $0.00011 | $0.00202 |
| Sonnet 5.5 | $0.00005 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
Figma 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 7d 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
This skill lets a coding agent operate Figma (desktop app) through Flue, a local shell-to-application bridge. The agent runs figma_bridge.py commands (compact build, tree, set, shot, sheet, or raw JS with eval) and gets structured JSON back. A small development plugin, Flue Bridge, runs in the open file and carries the jobs into the Plugin API.
agent shell ->
figma_bridge.py-> local daemon <- polled by the Flue Bridge plugin -> Figma Plugin API
When to use
The human requests work performed inside Figma - inspect the open file, build or restyle frames and components, apply effects, import images, review a design visually. A CLI agent cannot act inside Figma without a bridge like Flue.
How to proceed
- Read
FLUE.mdin this directory first. It explains how Flue works, the bridge contract and safety expectations. - If Flue is installed: also read
adapters/figma_adapter/APP.md(commands, spec format, connection recovery) and, for visual design work,adapters/figma_adapter/docs/design-recipes.md. - If Flue is not installed: tell the human. The install command is
pip install flue && flue setup. Do not install without explicit approval in the current session. - First run: the human imports the plugin once (Figma desktop > Plugins > Development > Import plugin from manifest...) and opens it in the file. Then
figma_bridge.py pairapproves it; no code to type.
Other apps
Flue also supports Photoshop, Illustrator, Premiere, After Effects, InDesign, Audition, Blender, Houdini, 3ds Max, Unity, and Microsoft Office through the same contract. One install covers all adapters.
Safety
Flue acts inside the human's live design file. Treat the human as the driver; prefer small, inspectable steps; every call is one undo step; do not save, publish or delete unless explicitly asked. Flue is MIT-licensed and reviewable on GitHub / PyPI before use.
What ships with it
1 file 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.
- 7d ago First seen · 23 lines · 27 tokens per session scan A 719851596c18
Figma is a skill published in the GitHub repository SFKislev/Flue (98 stars, last pushed 8d ago), licensed MIT. It adds 27 tokens to every session and 505 once invoked, about $0.0001 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 2026-10-19.
Other skills, from other repositories
awesome-design-md
Create a DESIGN.md style baseline BEFORE building UI. Use FIRST when no design draft exists — installs a proven visual style, then invoke frontend-design to implement. For borrowing a known product style, getting consistent typography/colors/spacing, or needing a fast visual starting point.
kirby-panel-and-blueprints
Designs Kirby 6 blueprints and Panel UI, including reuse/extends, programmable blueprints, value/display fields and areas. Use when changing Panel schemas or migrating legacy sections.
build-webgl-liquid-glass
Build production-ready GPU liquid-glass surfaces with liquid-gl for React or DOM UIs. Default for refractive cards, notifications, panels, GPU bevels, and WebGL glass.
design-explore
Explore 2-4 design options with pros/cons/criteria matrix before writing code. Use for L3-L4 tasks (refactors, architecture, new subsystems). Pairs with savedecision MCP tool.
favicon-exporter
Prepare and export favicon assets from Figma in common web sizes and formats.
ralph-figma
Extract Figma designs and build them as code with ralph-starter.