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 simiancraft/simiancraft-skills --skill playwright-storybook-flowsgit clone --depth 1 https://github.com/simiancraft/simiancraft-skillsWrote 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/simiancraft/simiancraft-skills/playwright-storybook-flows)<a href="https://agentmods.dev/skills/simiancraft/simiancraft-skills/playwright-storybook-flows"><img src="https://agentmods.dev/badge/skills/simiancraft/simiancraft-skills/playwright-storybook-flows/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/simiancraft/simiancraft-skills/playwright-storybook-flows"><img src="https://agentmods.dev/badge/skills/simiancraft/simiancraft-skills/playwright-storybook-flows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 119 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00158 | $0.02547 |
| Opus 5 | $0.00079 | $0.01273 |
| Sonnet 5 | $0.00032 | $0.00509 |
| Haiku 4.5 | $0.00016 | $0.00255 |
Grade A, and why
playwright-storybook-flows 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Storybook Flows: specialization of playwright-harness
Read playwright-harness first. This skill contains no Playwright
instruction and never will: all browser execution, screenshots, waits, and
assertions belong to playwright-harness. When a flow's evidence needs to land
on a PR, that is prove-work-on-github; when a captured image needs shrinking,
that is asset-optimization. This skill points to those seams and documents
exactly one thing: how to record human/machine shared steps for running a
flow.
Status: being authored. Definitions, step properties, the visualization spec, and the storage convention are locked; the authoring and reproduction loops are still being dictated and validated. Nothing in here is project-specific: the target Storybook is always parameterized (
STORYBOOK_URL), and flow locations are conventions, not paths into any one repo.
What a flow is
A flow is a sequence of steps that a human or an agent can take inside an application to demonstrate a specific feature.
The same document serves both readers. A human reads it as a walkthrough; an agent reads it as an executable rubric and reproduces it later on its own. If either reader would need a second document, the flow is miswritten.
Flows earn their keep in two situations:
- Issue reproduction. An issue arrives whose reproduction requires a series of steps; the flow illustrates and preserves those steps.
- Integration testing. A series of steps worth testing repeatedly is encapsulated as a flow, and an agent drives it.
Self-containment (the transportability rule)
Flows do not reference other flows. Every flow is internally consistent, internally self-contained, and therefore transportable.
During authorship it is fine for a flow to be described in terms of another flow ("log in, then..."); the referenced steps are then inlined into the new flow. If a detailed authentication flow exists and a new flow begins with "log in", the authentication steps are copied into the new flow, not linked. Assume the person or agent executing a flow has no knowledge of any other flow.
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 · 241 lines · 158 tokens per session scan A c17c472a6ee8
playwright-storybook-flows is a skill published in the GitHub repository simiancraft/simiancraft-skills (7 stars, last pushed 9d ago), licensed MIT. It adds 158 tokens to every session and 2,547 once invoked, about $0.0008 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.
Other skills, from other repositories
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
test-implement
Implements React/TypeScript unit, integration, and browser E2E tests with the repository's configured runner, mocks, setup, and browser harness. Use when creating or completing frontend tests and generated test skeletons.
visual-verification
Verify UI-facing changes by running a screenshot-analyze-verify loop across configured viewports, with a browser-tool priority cascade (Playwright MCP → Chrome DevTools MCP → CLI fallback → external skill fallback) and bounded iteration. Use after build/runtime verification passes and the diff includes…
fec-testing-strategy
A frontend testing strategy maps different risks to different checks, such as type checking, unit tests, component tests, integration tests, end-to-end tests, accessibility, security, and performance checks. It explains end-to-end testing as testing a complete user journey in a real browser.
visual-qa
Automated visual QA for a running frontend — screenshots the real rendered UI at the project's breakpoints and checks it against the project's own spec (tokens, layout rules, design language) AND its sibling screens, not hardcoded assumptions. Standalone on any frontend project; learns the project profile from docs/…
visual-diff
Visual Regression Testing — screenshot comparison before and after changes. Use when user wants to check for visual regressions, compare UI changes, or verify CSS/layout changes didn't break anything.