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 fellipeutaka/leon --skill figma-raw-geometrygit clone --depth 1 https://github.com/fellipeutaka/leonWrote 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/fellipeutaka/leon/figma-raw-geometry)<a href="https://agentmods.dev/skills/fellipeutaka/leon/figma-raw-geometry"><img src="https://agentmods.dev/badge/skills/fellipeutaka/leon/figma-raw-geometry.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 5.1 | $0.00066 | $0.01819 |
| Opus 5 | $0.00033 | $0.00910 |
| Sonnet 5 | $0.00013 | $0.00364 |
| Haiku 4.5 | $0.00007 | $0.00182 |
Grade A, and why
figma-raw-geometry scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl --fail-with-body --silent --show-error \\ How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use the Figma REST API as a measurement source. Return numeric measurements with field provenance and keep implementation assumptions separate from fetched values. A screenshot describes one rendered state; the node JSON exposes the state's geometry, transforms, visibility, and layer opacity.
1. Define the states and targets
Collect:
- the file key, decoded from the Figma URL;
- the containing frame or component-set id;
- every target state or variant id;
- the target layer mapping for each state; and
- the ordered prototype edges when reconstructing animation.
Decode a URL's node-id=123-456 as the Figma id 123:456, including URL
percent-decoding when necessary. Do not infer prototype order from variant
names. If an available Figma MCP metadata tool can enumerate a component set,
use it. Otherwise, request the component-set node with the REST nodes endpoint
and depth=1 to discover its direct variant children.
Map corresponding layers by structural path plus name. Include a sibling index when names repeat; do not assume that child node ids are shared between component variants.
Done when every requested state has a file key, root id, containing-frame id, and an unambiguous target-layer mapping, or an explicit unresolved reason.
2. Authenticate outside the conversation
Read FIGMA_TOKEN from the process environment. The token needs Figma's
file_content:read scope and access to the target file.
If the variable is absent, ask the user to set it in their own shell or secret manager and then confirm that it is available. Keep the secret out of chat, files, command output, and commits. The agent cannot export a value into the user's parent shell, so do not ask the user to paste the token into the conversation.
Done when a usable environment token is available without the token value being printed or persisted by this workflow.
3. Fetch the node JSON in bounded bulk
Request all required ids together when the URL and response are practical. If
the target set is too large, split it into bounded batches and pin the same
Figma version for every batch. Use depth to avoid fetching irrelevant
descendants; add geometry=paths only when vector path data is needed.
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.
- 8d ago First seen · 191 lines · 66 tokens per session scan A 2c0232c7dc1e
figma-raw-geometry is a skill published in the GitHub repository fellipeutaka/leon (5 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 1,819 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.