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 skyfox675/agents-skills --skill figma-specsgit clone --depth 1 https://github.com/skyfox675/agents-skillsWrote 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/skyfox675/agents-skills/figma-specs)<a href="https://agentmods.dev/skills/skyfox675/agents-skills/figma-specs"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/figma-specs/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/skyfox675/agents-skills/figma-specs"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/figma-specs.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 | $0.00222 | $0.01940 |
| Opus 5 | $0.00111 | $0.00970 |
| Sonnet 5 | $0.00044 | $0.00388 |
| Haiku 4.5 | $0.00022 | $0.00194 |
Grade A, and why
figma-specs 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma Specs: track design drift without re-touching everything
The pain: designs change, and the Figma file's organization changes too — pages, sections, and frames get moved and renamed. Every move introduces tiny differences (a spacing tweak, a color shift, a renamed layer), they accumulate, and the team re-touches code constantly, often for changes that aren't really changes. This skill fixes that by tracking the design the way the design actually identifies itself, not by where it currently sits — and it does so without depending on any paid Figma feature.
The key idea: anchor on stable identity, never on location
Figma node IDs and published component / style / variable keys are stable across moves, renames, and reorganization, and they come back from an ordinary Figma read. A frame dragged to another page keeps its node ID; a published component keeps its key wherever it lives. So key every spec to those ids, never to a page/section/frame name or a position — those are exactly what designers move. When something moves, its id is unchanged and the link holds; the only thing that changed is a human-readable locator, which the refresh updates without touching code.
The design→code map is repo-owned (Code Connect optional)
Drift is only actionable if you know which code a changed component maps to. Do not depend on Figma Code Connect for this — it needs paid Dev Mode and a publishing step that may not be available or allowed. Instead the mapping lives in the spec itself and is built locally:
- Discover by name. Dispatch the cheap
scoutagent to grep the codebase for the component/token whose name matches the Figma component or variable (e.g. FigmaButton/Primary→src/ui/Button.tsx). Record the candidatefile:lineand a confidence. - Confirm once. For low-confidence or ambiguous matches, ask the operator (an emoji-answerable comment or interactive question, as the recon skills do) and record the answer. A confirmed mapping is permanent until the code moves.
- Optional accelerator: if Code Connect happens to be set up,
get_code_connect_mapcan seed/verify the mapping for free — use it when present, never require it.
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.
- 10d ago First seen · 76 lines · 222 tokens per session scan A ec5f8add94ad
figma-specs is a skill published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 222 tokens to every session and 1,940 once invoked, about $0.0011 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.