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 aziontech/webkit --skill webkit-data-vizgit clone --depth 1 https://github.com/aziontech/webkitWrote 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/aziontech/webkit/webkit-data-viz)<a href="https://agentmods.dev/skills/aziontech/webkit/webkit-data-viz"><img src="https://agentmods.dev/badge/skills/aziontech/webkit/webkit-data-viz/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/aziontech/webkit/webkit-data-viz"><img src="https://agentmods.dev/badge/skills/aziontech/webkit/webkit-data-viz.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 | $0.00114 | $0.02385 |
| Opus 5.5 | $0.00046 | $0.00954 |
| Sonnet 5.5 | $0.00023 | $0.00477 |
| Haiku 4.5 | $0.00011 | $0.00238 |
Grade A, and why
webkit-data-viz 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 1mo 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: webkit-data-viz
Purpose
A chart muddy in one theme, or spinning forever on an empty dataset, is broken the same way a
mis-tokened button is — and Azion Console is an observability product, so charts are a primary
surface, not decoration. This skill is the token adapter: it takes the charting decisions and
realizes them in @aziontech/theme. For chart-form (which form answers which question) and palette
theory (categorical / sequential / diverging, contrast math, color-blind pairing), see the generic
dataviz skill; this skill covers only mapping that onto @aziontech/theme tokens — deriving every
color from the --color-* families (never hex), re-reading computed tokens on a data-theme change so
a canvas re-themes (SVG re-themes for free), and rendering the chart's loading / empty / error surface
with webkit components. It does not pick your charting library — canvas or SVG rendering is a
consumer choice; the tokens below are not.
How to use
/webkit-data-viz— apply the token mapping to any chart, dashboard, or KPI tile you build in this conversation. Pick the form and the palette kind with the genericdatavizskill first, then map it onto tokens here./webkit-data-viz <file>— review the file's charts and report, per gap: the quoted line, the token problem (off-token color, no theme re-read, missing state, non-tabular figures), and the concrete token-mapped fix. Form and palette-kind review belong to the genericdatavizskill.
How to find the components + tokens
Never guess an import path or a hex value. Resolve both from the contract:
- Components (
Skeleton,EmptyState,Message,CardBox,StatusIndicator): ask the webkit MCP —suggest_componentin plain words ("empty state", "stat card") — or read theimportskeys innode_modules/@aziontech/webkit/catalog.json. A subpath that is not a key there does not exist. - Tokens: read the
tokenstree in the samecatalog.json(the--color-*families:blue,violet,green,orange,yellow,red, each50→950; plus--success,--warning,--danger,--info), or the human catalog innode_modules/@aziontech/webkit/docs/STYLEGUIDE.md. Derive every chart color from these — never a raw hex.
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.
- 1mo ago First seen · 178 lines · 114 tokens per session scan A b3949e791807
webkit-data-viz is a skill published in the GitHub repository aziontech/webkit (3 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 2,385 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
monorepo-management
Sets up or audits a monorepo workspace: tool selection, package naming, shared tooling, inter-package dependencies, selective CI, and versioning strategy. Invoked when the user asks to set up a monorepo, add a workspace, or manage multiple packages in a single repository.
bazel-monorepo-expert
Expert knowledge for managing large-scale Bazel monorepos with multiple services, shared libraries, and cross-cutting concerns. Use for workspace structure, visibility, and dependency management.
pnpm
Skill "pnpm" from pledgeandgrow/pledge-skills, covering pnpm documentation skill, key benefits, file index, quick start and install pnpm.
data-dashboard
Build a dense, data-heavy screen - an analytics console or a trading terminal - with real charts drawn from tokens: candlestick, volume, depth, stacked area, waterfall, scatter, correlation matrix, donut, gauge, sparklines, heatmaps and order books. Use when the request is a dashboard, terminal, monitoring view, data…
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.
fast-typescript-check
Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…