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 agentmods add skills/prowler-cloud/prowler/playwrightnpx skills add prowler-cloud/prowler --skill playwrightgit clone --depth 1 https://github.com/prowler-cloud/prowlerWhat 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 | $0.00050 | $0.02403 |
| Opus 5 | $0.00025 | $0.01202 |
| Sonnet 5 | $0.00010 | $0.00481 |
| Haiku 4.5 | $0.00005 | $0.00240 |
Grade A, and why
playwright 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 3d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- playwright — 94% identical, 21 lines differ
- e2e-tester — 92% identical, 311 lines differ
How it starts
The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Workflow (MANDATORY If Available)
⚠️ If you have Playwright MCP tools, ALWAYS use them BEFORE creating any test:
- Navigate to target page
- Take snapshot to see page structure and elements
- Interact with forms/elements to verify exact user flow
- Take screenshots to document expected states
- Verify page transitions through complete flow (loading, success, error)
- Document actual selectors from snapshots (use real refs and labels)
- Only after exploring create test code with verified selectors
If MCP NOT available: Proceed with test creation based on docs and code analysis.
Why This Matters:
- ✅ Precise tests - exact steps needed, no assumptions
- ✅ Accurate selectors - real DOM structure, not imagined
- ✅ Real flow validation - verify journey actually works
- ✅ Avoid over-engineering - minimal tests for what exists
- ✅ Prevent flaky tests - real exploration = stable tests
- ❌ Never assume how UI "should" work
File Structure
tests/
├── base-page.ts # Parent class for ALL pages
├── helpers.ts # Shared utilities
└── {page-name}/
├── {page-name}-page.ts # Page Object Model
├── {page-name}.spec.ts # ALL tests here (NO separate files!)
└── {page-name}.md # Test documentation
File Naming:
- ✅
sign-up.spec.ts(all sign-up tests) - ✅
sign-up-page.ts(page object) - ✅
sign-up.md(documentation) - ❌
sign-up-critical-path.spec.ts(WRONG - no separate files) - ❌
sign-up-validation.spec.ts(WRONG)
Selector Priority (REQUIRED)
// 1. BEST - getByRole for interactive elements
this.submitButton = page.getByRole("button", { name: "Submit" });
this.navLink = page.getByRole("link", { name: "Dashboard" });
// 2. BEST - getByLabel for form controls
this.emailInput = page.getByLabel("Email");
this.passwordInput = page.getByLabel("Password");
// 3. SPARINGLY - getByText for static content only
this.errorMessage = page.getByText("Invalid credentials");
this.pageTitle = page.getByText("Welcome");
// 4. LAST RESORT - getByTestId when above fail
this.customWidget = page.getByTestId("date-picker");
// ❌ AVOID fragile selectors
this.button = page.locator(".btn-primary"); // NO
this.input = page.locator("#email"); // NO
What ships with it
1 file 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.
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.
- 3d ago First seen · 327 lines · 50 tokens per session scan A ed9d005e908c
playwright is a skill published in the GitHub repository prowler-cloud/prowler (14,736 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 2,403 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
self-verify-beacon-in-sandbox
Verify a Beacon change end to end by running a real Claude Code session inside a disposable Linux cloud sandbox and checking that Beacon captured what the agent actually did. Use when asked to verify, validate, test, or prove that a Beacon change works for real rather than just compiling; when asked whether telemetry…
pick-integ
Recommend which integration tests to run, based on the integ ledger (staleness / last result) plus the code areas touched by recent commits. Outputs a prioritized list of /run-integ commands. Use before a release, after a batch of merges, or when unsure what integ coverage a change needs.
new-integ
Scaffold a new integration test for cdkd. Creates a minimal CDK app with the specified AWS resources for deploy/destroy E2E testing.
ponytail-sec-audit
Full project security audit. Scans the entire codebase across three passes: code that shouldn't exist, all dependencies assessed, all hardening findings. Produces a comprehensive numbered report with blast-radius narrative. Persists findings to .ponytail-sec/ for cross-scan tracking. For per-diff review use…
ponytail-sec
Security companion for active development. Scopes to the current diff or changed files. Three passes: YAGNI code review, new-dep assessment, and up to 3 material hardening findings. Lean by design — surfaces the one thing to fix before merging, not a backlog. Use ponytail-sec-audit for a full project scan.
selenium-ui-test-generator
Generates Selenium WebDriver tests for React/Angular front-ends with STRICT loop prevention. Triggers on: "test UI", "generate Selenium tests", "test React app", "create E2E tests", "test front-end". WARNING: UI tests cost 3x more than unit tests -- generate selectively.