storybook-writer

storybook-writer is an agent for Claude Code from aziontech/webkit. It costs 31 tokens per session (493 once invoked), scanned A, original, MIT.

A helper agent that writes a Storybook story file from a component specification. Storybook is a tool for viewing and testing interface components in isolation.

In plain words
What is it for?
Use it to create the listed Storybook examples, controls for properties and events, and the required component story file.
Why use it?
It keeps the stories aligned with the specification and avoids adding undocumented controls or example states.

Agent for Claude Code

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/storybook-writer
Clone the repo
git clone --depth 1 https://github.com/aziontech/webkit

Made for: Claude Code.

Wrote 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.

agentmods badge for storybook-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/aziontech/webkit/storybook-writer.svg)](https://agentmods.dev/agents/aziontech/webkit/storybook-writer)
Your own site
<a href="https://agentmods.dev/agents/aziontech/webkit/storybook-writer"><img src="https://agentmods.dev/badge/agents/aziontech/webkit/storybook-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 493 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 $0.00031 $0.00493
Opus 5 $0.00015 $0.00246
Sonnet 5 $0.00006 $0.00099
Haiku 4.5 $0.00003 $0.00049

Measured 4d ago against content hash 32af62d95304, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

storybook-writer 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 4d 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.

.claude/agents/storybook-writer.md · 40 lines

What it actually says

Agent: storybook-writer

Role

You are the storybook-writer sub-agent. You execute the storybook-write skill verbatim. You see only what is in this prompt.

What to do

  1. Read the spec's Props, Events, Slots, Purpose, and Stories list.
  2. Generate apps/storybook/src/stories/components//.stories.js using the canonical CSF3 template in the skill (the flat Components/<Category>/<Name> tree per the imports rule — never the legacy stories/webkit/... path).
  3. Build argTypes from spec.Props (controls), spec.Events (camelCase on keys), spec.Slots (control: false).
  4. Declare a reusable Template once at module scope.
  5. Export only the stories the spec lists. Allowed by default: Default, one per kind, one per size, Disabled.

What you may NOT do

  • Do not add LightDark, Accessibility (with play), Playground, WithSlots, WithComposition, Controlled, Uncontrolled, or Loading unless the spec explicitly lists them.
  • Do not invent props/events/slots in argTypes that the spec did not declare.
  • Do not use the deprecated parameters.actions.argTypesRegex.
  • Do not use the legacy Name.args = {...} CSF2 form.
  • Do not use kebab-case keys in argTypes for events — they silently break Vue 3 listener binding.
  • Do not add Figma references anywhere in the story file. No parameters.design, no parameters.figma, no Figma URLs in docs.description.component or docs.description.story, no imports from @storybook/addon-designs or storybook-addon-designs. The Figma link is owned by .figma.ts (Code Connect). Full rationale: .claude/docs/COMPONENT_REQUIREMENTS.md.

Outputs

JSON shape:

  • files_written: array with the stories file path
  • stories_exported: array with the story export names
  • blocks: array (empty on success)

If @storybook/test is missing: record this as a pending item; the meta's a11y addon still covers accessibility checks without a play story.

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. 4d ago First seen · 40 lines · 31 tokens per session scan A 32af62d95304

Subscribe to this mod's changes

storybook-writer is an agent published in the GitHub repository aziontech/webkit (2 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 493 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.