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 cyberuni/cyber-figma --skill inspect-figma-filegit clone --depth 1 https://github.com/cyberuni/cyber-figmaWrote 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/cyberuni/cyber-figma/inspect-figma-file)<a href="https://agentmods.dev/skills/cyberuni/cyber-figma/inspect-figma-file"><img src="https://agentmods.dev/badge/skills/cyberuni/cyber-figma/inspect-figma-file/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/cyberuni/cyber-figma/inspect-figma-file"><img src="https://agentmods.dev/badge/skills/cyberuni/cyber-figma/inspect-figma-file.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 | $0.00032 | $0.01608 |
| Opus 5 | $0.00016 | $0.00804 |
| Sonnet 5 | $0.00006 | $0.00322 |
| Haiku 4.5 | $0.00003 | $0.00161 |
Grade A, and why
inspect-figma-file 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 10d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inspect Figma File
When to use
When the user points at a Figma file or a specific frame and wants to know what is in it — page and frame structure, a node's properties, published components or styles, or which file a URL refers to.
Not for exporting images — use export-figma-assets for that.
Ensure cyber-figma CLI
See the Ensure cyber-figma CLI section of the init-figma skill. If FIGMA_ACCESS_TOKEN is unset, run init-figma first.
If a command below exits 2 (usage error), the spelling has moved — confirm it with cyber-figma --help and cyber-figma <resource> --help rather than guessing. The global flags (--token, --team, --toon, --json, --full) and the exit codes are stable.
The one rule that matters
GET file is the single most expensive call in the Figma API (rate-limit tier 1), it is not paginated, and it returns the entire document tree. On a View or Collab seat the whole month's budget is about 6 such calls. So:
Never fetch the full tree first. Narrow before you fetch.
The ladder, cheapest first:
| Step | Command | Tier | Returns |
|---|---|---|---|
| 1 | file meta |
3 | name, project folder, last touched, editor type, role |
| 2 | file get --depth 1 |
1 | pages only |
| 3 | file get --depth 2 |
1 | pages + top-level objects |
| 4 | node get --ids <ids> |
1 | just the named subtrees |
| 5 | file get (no flags) |
1 | everything — last resort |
Instructions
1. Resolve the file key (and node id) from the URL
Figma URLs carry both:
https://www.figma.com/design/<file-key>/<title>?node-id=<node-id>
The segment after /design/ (or the older /file/) is the file key. ?node-id= is a specific node — if the user's link has one, they are almost certainly asking about that node, not the whole file. Say so and go straight to step 4.
Note that node-id in a URL is dash-separated (12-345) while the API uses a colon (12:345). Pass the URL through the CLI rather than hand-editing it where possible.
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.
- 10d ago First seen · 127 lines · 32 tokens per session scan A babd8ddfedbb
inspect-figma-file is a skill published in the GitHub repository cyberuni/cyber-figma (0 stars, last pushed 5d ago), licensed MIT. It adds 32 tokens to every session and 1,608 once invoked, about $0.0002 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.