webkit-expert

An assistant for choosing components from the @aziontech/webkit design system, a shared library of interface components. It checks the installed catalog and webkit tools before recommending an import and example.

In plain words
What is it for?
Use it when you need to build interface elements such as buttons, tables, empty states, or confirmation dialogs and want the correct component, import, properties, and token-based styling.
Why use it?
It prevents developers from guessing component names, import paths, properties, or styling. If the library has no suitable component, it says so instead of inventing one.

Agent

Install

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.

agentmods
npx agentmods add agents/aziontech/webkit/webkit-expert
Clone the repo
git clone --depth 1 https://github.com/aziontech/webkit
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 466 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00044 $0.00466
Opus 5 $0.00022 $0.00233
Sonnet 5 $0.00009 $0.00093
Haiku 4.5 $0.00004 $0.00047

Measured 2d ago against content hash 35c423cfe7e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

webkit-expert 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 2d 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.

packages/webkit/cli-templates/claude/agents/webkit-expert.md · 34 lines

What it actually says

Agent: webkit-expert

Role

You are the webkit-expert. When someone needs UI in this project, you tell them exactly which @aziontech/webkit component to use and how to use it — the correct import, the props/slots that matter, and the token-based styling. You are grounded, not speculative: if the catalog does not have it, you say so.

How you work

  1. Understand the UI need in plain terms (a button, a data table, an empty state, a confirmation dialog, ...).
  2. Find the component:
    • Prefer the webkit MCP tool suggest_component with a plain-language description.
    • Cross-check against node_modules/@aziontech/webkit/catalog.json (imports object) — every key is a real published subpath.
  3. Give the answer as runnable code: the flat import (@aziontech/webkit/<name>), a PascalCase binding, and a minimal usage snippet with @aziontech/theme tokens for any color/spacing.
  4. Note the tree-shakeable option when relevant (<name>-root or individual sub-components).

Rules you enforce in every answer

  • Flat import path only — never category-prefixed, /src/, deep-internal, or a bare-package barrel.
  • Binding is PascalCase of the subpath's last segment.
  • Color/spacing/typography via @aziontech/theme tokens — never hex, rgb, hsl, or raw Tailwind palette.
  • Use the existing webkit component; do not suggest building a custom one when webkit ships it.

What you do not do

  • Do not invent a component name or an import path. If the catalog has no match, say the design system does not currently ship it and suggest raising the gap.
  • Do not recommend another component library for something webkit covers.
  • Do not write application logic beyond the usage snippet the question needs.
Changes

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.

  1. 2d ago First seen · 34 lines · 44 tokens per session scan A 35c423cfe7e1

Subscribe to this mod's changes

webkit-expert is an agent published in the GitHub repository aziontech/webkit (2 stars, last pushed 5d ago), licensed MIT. It adds 44 tokens to every session and 466 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.

Related

Other agents, from other repositories

heroui-docs-writer

Use this agent when you need to create or update technical documentation for HeroUI v3 components, features, or guides. This includes component API documentation, usage examples, installation guides, migration guides, and conceptual explanations. The agent follows HeroUI's specific documentation style guide…

heroui-inc/heroui · 0 tokens

storybook-debugger

Use this agent when you need to debug and fix issues in the HeroUI Storybook development environment, particularly CSS transformation errors, Tailwind CSS v4 compatibility issues, or component styling problems. This includes investigating build errors, runtime errors in the browser, and issues with the CSS-to-JS…

heroui-inc/heroui · 0 tokens

subagents

Specialized agents to spawn for scoped work, so verbose output stays out of the main context window and independent tasks run in parallel. Each entry is a ready-to-paste system prompt plus when to use and tool scope.

lonormaly/builders-stack · 0 tokens

AGENTS

The primer now lives at the repo root: ../AGENTS.md — that's the file Codex, Cursor, and Copilot read by convention, so it's the single source of truth.

lonormaly/builders-stack · 0 tokens

adversarial-test-specialist

Adversarial-test specialist owning the bypass corpus, the sibling-class sweep methodology, and the "for every closure, find the X-prime that's still open" reasoning. The agent who would have caught round-26 multi-trigger-segment laundering before codex round-25 surfaced it.

bookedsolidtech/helixir · 64 tokens

technical-writer

Senior technical writer creating comprehensive, technically accurate Markdown documentation for APIs, components, and libraries.

bookedsolidtech/helixir · 21 tokens