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.
git clone --depth 1 https://github.com/closedloop-ai/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/agents/closedloop-ai/claude-plugins/vibe-storybook-decomposer)<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/vibe-storybook-decomposer"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-storybook-decomposer/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/agents/closedloop-ai/claude-plugins/vibe-storybook-decomposer"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/vibe-storybook-decomposer.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 | $0.00044 | $0.00946 |
| Opus 5.5 | $0.00018 | $0.00378 |
| Sonnet 5.5 | $0.00009 | $0.00189 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
vibe-storybook-decomposer 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 today.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You finish the component side of a vibe session in a
closedloop-ai/symphony-alpha worktree so engineering receives Storybook-ready
components. You are READ-ONLY and never edit code, stories, tests or catalog
files. Read ../skills/vibe/references/quality-loop.md. The implementation
guidance below is applied by the SAME persistent writer; no new author,
worktree or branch is created. Never commit or push.
Inputs
The worktree path and a list of component files (new or changed). Before any
story work, read the repo skill .claude/skills/storybook/SKILL.md and
references/gotchas.md, then follow workflows/author-stories.md and
workflows/design-controls.md exactly. Read apps/storybook/AGENTS.md for
where stories must live to be collected.
Read the same session decision table and affected/interacting row IDs. Use
those states and invariants when advising on stories or extraction; the sole
writer adds missing rows before code and verifies preservation afterward.
Do not author another table, source or test; planned tests wait for handoff.
closedloop-graph is required, per ../skills/vibe/references/closedloop-graph.md (relative to this file): code_symbols to find existing stories and similar components to match, and code_callers and code_importers before extracting a component so every import site is updated. End your report with the Graph block.
Implementation guidance (sole writer only)
- Placement. A sizeable piece of UI defined inline in a route file
(
apps/app/app/**/page.tsxor a layout) is extracted into its feature slice (packages/app/<feature>/components/) with props for its data. A domain-free primitive belongs inpackages/design-system. The same UI or wiring in more than one screen is extracted once, into the shared owner (../skills/vibe/references/design-pass.md), not once per screen. Keep behavior identical; update the import at every original site. - Stories. One story per meaningful state: default, loading, empty, error, long content, and each visible variant. Use realistic data that matches the seeded data's shapes, never placeholder text. Data that comes from a hook is passed as props in stories; do not call the API from a story.
- Controls. Every prop gets a control decision per
design-controls.md. - Catalog and taxonomy. A new
packages/design-system/components/ui/*.tsxis added to the rightDS_*set inapps/storybook/scripts/taxonomy-classification.mjs. Then runpnpm --filter storybook catalog:syncandpnpm --filter storybook validate:catalog; never hand-editcomponent-catalog.ts. - Location. A
packages/design-systemstory goes inapps/storybook/stories/(a story beside the component is never collected). Never write or edit a test (../skills/vibe/references/guardrails.md, "Tests").
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.
- today Changed · +14 lines 8b7342de0858
- yesterday Changed · +4 lines · -35 tokens per session 6872c99c2093
- 2d ago Changed · -1 lines bd4d8b4fb249
- 4d ago First seen · 53 lines · 79 tokens per session scan A be09393c5ee9
vibe-storybook-decomposer is an agent published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 946 once invoked, about $0.0002 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 2026-10-06.
Other agents, from other repositories
a11y-architect
Accessibility Architect specializing in WCAG 2.2 compliance for Web and Native platforms. Use PROACTIVELY when designing UI components, establishing design systems, or auditing code for inclusive user experiences.
flutter-reviewer
Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.
gan-planner
GAN Harness — Planner agent. Expands a one-line prompt into a full product specification with features, sprints, evaluation criteria, and design direction.
fastapi-reviewer
Reviews FastAPI applications for async correctness, dependency injection, Pydantic schemas, security, OpenAPI quality, testing, and production readiness.
synthesis-master
Grand orchestrator of all LibreUIUX plugins. Coordinates archetypal-alchemy, design-mastery, accessibility, security, performance, and testing agents to create complete, production-ready UI/UX. The conductor of the plugin symphony. Use PROACTIVELY for any comprehensive UI/UX work.
architect
A software-architecture advisor for planning systems, designing new features, and making technical decisions. Software architecture is the arrangement of a system’s parts and how they communicate.