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 agentmods add skills/smk-labs/claude-plugins/fignpx skills add smk-labs/claude-plugins --skill figgit clone --depth 1 https://github.com/smk-labs/claude-pluginsWrote 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/smk-labs/claude-plugins/fig)<a href="https://agentmods.dev/skills/smk-labs/claude-plugins/fig"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/fig.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 | $0.00063 | $0.01463 |
| Opus 5 | $0.00032 | $0.00732 |
| Sonnet 5 | $0.00013 | $0.00293 |
| Haiku 4.5 | $0.00006 | $0.00146 |
Grade A, and why
fig 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 5d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Some ideas are explained better by a 5-second looping animation than by 100 lines of text.
Sketch the figure in ASCII first: static layout, labelled motion, loop length. Get a yes before writing the svg.
After building, look at the rendered file as a stranger would and refine once before handing back. ASCII covers structure; visual issues (collisions, weak contrast, orphan elements, dated chrome, loose components that should be grouped) only appear on screen.
Guidelines
- Subject fit. Invent a visual metaphor for this specific idea. The same concept can be drawn many ways (a flow as a path, ripples, falling sand, expanding rings; a network as nodes, a constellation, a colony of pulses). Reach past the obvious shape.
- One accent. One thing moves meaningfully, in one accent colour. Show direction through motion, not a second hue.
- Loop cleanly. End frame equals start frame, or fade-pause-fade. No jerk at the seam.
- Caption economy. One short title plus a 5-word caption at most. The figure carries it.
- Calm by default. 5 to 10 second loops,
easeInOutCubicoreaseInOutSine. Bounce and elastic read as toy.
Pick fonts, palette, background, canvas, and layout for the subject. Nothing below is a default.
Stack
One HTML file, one inline <svg>, motion in CSS. No JavaScript, no CDN, no build step.
That is not taste, it is the delivery format. A fig is made to be embedded: as an <img> in a report, as an attachment in an email, as a paste in a slide. Every one of those lifts the <svg> out and renders it as its own document. In that document no script ever runs and nothing is fetched. A figure animated from JavaScript freezes on its first frame there, or shows nothing at all. CSS @keyframes and SMIL are the only motion that survives the trip.
Five rules that document imposes. Break one and the figure dies quietly, looking fine on your screen:
- Everything lives inside
<svg>. The<style>, the gradients, the filters. Only the svg element travels; whatever sits in<head>is left behind. xmlns="http://www.w3.org/2000/svg"on the svg. An HTML parser forgives a missing namespace. An<img>renders nothing without it.- Strict XML. Every tag closes, and no bare
<or&anywhere, including inside a CSS comment, where it is easiest to forget. Write<and&. - No
<script>, no event handlers, norequestAnimationFrame. - RTL is declared, never inherited.
dir="rtl"is an HTML attribute and means nothing to an svg document, and the host page's direction stops at the image boundary. Putstyle="direction:rtl"on the<svg>itself, or everytext-anchor="start"label jumps to the wrong side of its anchor.
What ships with it
3 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.
- 5d ago First seen · 100 lines · 63 tokens per session scan A 903153fa1f9c
fig is a skill published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 1,463 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
brainstorm-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.
ab-test-analysis
Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
outcome-roadmap
Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent. Rewrites initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps, making a roadmap more strategic, or rewriting feature lists as outcomes.
pre-mortem
Run a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go…
shipping-artifacts
The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded…