Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add strongeron/storybook-workbench/plugin install storybook-workbenchWrote 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/strongeron/storybook-workbench/sb-audit)<a href="https://agentmods.dev/skills/strongeron/storybook-workbench/sb-audit"><img src="https://agentmods.dev/badge/skills/strongeron/storybook-workbench/sb-audit/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/strongeron/storybook-workbench/sb-audit"><img src="https://agentmods.dev/badge/skills/strongeron/storybook-workbench/sb-audit.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 | $0.00050 | $0.01716 |
| Opus 5 | $0.00025 | $0.00858 |
| Sonnet 5 | $0.00010 | $0.00343 |
| Haiku 4.5 | $0.00005 | $0.00172 |
Grade A, and why
sb-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sb-audit — drift survey + decision board
The periodic gate. Surveys the catalog, seeds the ledger, names consolidation candidates.
Run it
SKILL=${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}
CORE=${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}
"$SKILL/scripts/audit-drift.sh" # naming drift across stories
"$SKILL/scripts/audit-archived.sh" # L1/L2/L3 preservation surveillance (HEAVY warning)
"$CORE/scripts/find-stories-by-tag.sh" decision:pending # stale decisions needing a nudge
"$CORE/scripts/extract-component-usage.sh" # REFRESH real prop-usage → component-usage.json (auto, no hand-edits)
"$SKILL/scripts/audit-controls.sh" . # Controls-panel coverage: component stories missing argTypes + manager showPanel
"$CORE/scripts/refresh-usage.sh" --docs . # ONE-COMMAND refresh: components + tokens + routes + health JSON + re-stamp per-component usage MDX
# App flow + component lists: re-run the repo-local app-graph extractor if present, then VALIDATE it
[ -f .storybook/scripts/extract-app-graph.mjs ] && node .storybook/scripts/extract-app-graph.mjs # refresh app-graph.json + component-pages.json
[ -f .storybook/app-graph.json ] && node -e 'const g=require("./.storybook/app-graph.json"); const by={}; for(const e of g.edges) by[e.attribution]=(by[e.attribution]||0)+1; console.log("flow edges by attribution:", by, "| unresolved:", g.unresolvedEdges.length); for (const u of g.unresolvedEdges) console.log(" UNRESOLVED", u.provenance, "→", u.to, "—", u.reason)'
Sequence — don't run all six cold. Start with audit-drift.sh (cheap, names consolidation
candidates). The HEAVY audit-archived.sh L1/L2/L3 scan only earns its cost once the catalog is
sizable — skip it under ~20 chosen stories (nothing to prune yet). Run audit-controls.sh +
extract-component-usage.sh when you're checking coverage; refresh-usage.sh --docs is the
all-in-one rendered refresh — run it last, not alongside the individual extractors it supersedes.
What ships with it
14 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.
- agents/openai.yaml 730 B
- CONTEXT.md 14 KB
- references/anti-patterns.md 15 KB
- references/galleries-and-tags.md 16 KB
- references/lifecycle-tags.md 12 KB
- references/propagate-workflow.md 18 KB
- scripts/audit-archived.sh 8.4 KB runs code
- scripts/audit-controls.sh 4.5 KB runs code
- scripts/audit-drift.sh 4.3 KB runs code
- scripts/extract-component-usage.sh 11 KB runs code
- scripts/find-stories-by-tag.sh 3.3 KB runs code
- scripts/prune-to-ledger.sh 7.2 KB runs code
- scripts/refresh-usage.sh 3.5 KB runs code
- templates/design-decisions.md 1.8 KB
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.
- 12d ago First seen · 97 lines · 50 tokens per session scan A c6995d6e1bcd
sb-audit is a skill published in the GitHub repository strongeron/storybook-workbench (33 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 1,716 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
21st-ui
Find, install, and generate UI with 21st.dev. Use when the user asks for a UI component (pricing table, hero, navbar, dashboard, form, etc.), wants design inspiration, needs a brand logo as an SVG component, or wants to generate new UI from a prompt.
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
openai-frontend-design
Use for new frontend applications, dashboards, games, creative websites, hero sections, and visually driven UI from scratch, or when the user explicitly asks for a redesign/restyle/modernization. Builds from clean, airy, high-taste, readable image-generated concept design with section-specific references, faithful…
interaction-skill
Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…
layout-skill
Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…