Prowler is an open-source cloud security platform that checks cloud environments for security issues and compliance with standards such as CIS, NIST, and GDPR. Security teams use it to assess configurations, prioritize findings, produce reports, and guide remediation.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/prowler-cloud/prowlernpx agentmods add skills/prowler-cloud/prowler/prowler-test-uiWrote 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/prowler-cloud/prowler/prowler-test-ui)<a href="https://agentmods.dev/skills/prowler-cloud/prowler/prowler-test-ui"><img src="https://agentmods.dev/badge/skills/prowler-cloud/prowler/prowler-test-ui.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.02072 |
| Opus 5 | $0.00026 | $0.01036 |
| Sonnet 5 | $0.00010 | $0.00414 |
| Haiku 4.5 | $0.00005 | $0.00207 |
Grade A, and why
prowler-test-ui 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 8d 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generic Patterns: For base Playwright patterns (Page Object Model, selectors, helpers), see the
playwrightskill. This skill covers Prowler-specific conventions only.
Prowler UI Test Structure
ui/tests/
├── base-page.ts # Prowler-specific base page
├── helpers.ts # Prowler test utilities
└── {page-name}/
├── {page-name}-page.ts # Page Object Model
├── {page-name}.spec.ts # ALL tests (single file per feature)
└── {page-name}.md # Test documentation (MANDATORY - sync with spec.ts)
MANDATORY Checklist (Create or Modify Tests)
⚠️ ALWAYS verify BEFORE completing any E2E task:
When CREATING new tests
-
{page-name}-page.ts- Page Object created/updated -
{page-name}.spec.ts- Tests added with correct tags (@TEST-ID) -
{page-name}.md- Documentation created with ALL test cases - Test IDs in
.mdmatch tags in.spec.ts
When MODIFYING existing tests
-
{page-name}.mdMUST be updated if:- Test cases were added/removed
- Test flow changed (steps)
- Preconditions or expected results changed
- Tags or priorities changed
- Test IDs synchronized between
.mdand.spec.ts
Quick validation
# Verify .md exists for each test folder
ls ui/tests/{feature}/{feature}.md
# Verify test IDs match
grep -o "@[A-Z]*-E2E-[0-9]*" ui/tests/{feature}/{feature}.spec.ts | sort -u
grep -o "\`[A-Z]*-E2E-[0-9]*\`" ui/tests/{feature}/{feature}.md | sort -u
[!IMPORTANT] ❌ An E2E change is NOT considered complete without updating the corresponding
.mdfile.
MCP Workflow - CRITICAL
⚠️ MANDATORY: If Playwright MCP tools are available, ALWAYS use them BEFORE creating tests.
- Navigate to target page
- Take snapshot to see actual DOM structure
- Interact with forms/elements to verify real flow
- Document actual selectors from snapshots
- Only then write test code
Why: Prevents tests based on assumptions. Real exploration = stable tests.
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.
- 8d ago First seen · 283 lines · 51 tokens per session scan A 39697df43aeb
prowler-test-ui is a skill published in the GitHub repository prowler-cloud/prowler (14,767 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 2,072 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
bun-runtime
Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support.
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
compiler-port
Port a compiler pass from TypeScript to Rust. Gathers context, plans the port, implements in a subagent with test-fix loop, then reviews.
verify
Build, launch, drive, and screenshot the OpenNOW Electron settings UI on Windows.
break
Renders a component you choose in every state and scenario on a temporary page and stress tests it.
visual-qa
MUST USE after building/changing any UI or when asked whether a page, component, or TUI looks right. Rigorous visual QA across web/page and terminal UIs. Prefer browser:control-in-app-browser for unauthenticated browser/page QA in Codex, then Playwright/agent-browser/dev-browser. Captures screenshot/TUI evidence with…