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
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 prowler-cloud/prowler --skill prowler-tourgit clone --depth 1 https://github.com/prowler-cloud/prowlerWrote 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-tour)<a href="https://agentmods.dev/skills/prowler-cloud/prowler/prowler-tour"><img src="https://agentmods.dev/badge/skills/prowler-cloud/prowler/prowler-tour/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/prowler-cloud/prowler/prowler-tour"><img src="https://agentmods.dev/badge/skills/prowler-cloud/prowler/prowler-tour.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00041 | $0.00973 |
| Opus 5.5 | $0.00016 | $0.00389 |
| Sonnet 5.5 | $0.00008 | $0.00195 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
prowler-tour 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 1mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prowler-tour
Report-only. This skill never edits tour files or UI files; it inspects the change, reports drift it finds between tours and the covered UI, and recommends actions for the developer to apply.
Early-exit rule
Run this check first. Most UI edits are not tour-related — exit cheaply.
-
Glob
ui/lib/tours/*.tour.ts. -
For each tour, check whether any
coversFilesglob pattern matches any file in the current change. -
If no tour matches, respond exactly:
No tour affected — skipping alignment check
and exit. Do not proceed to the checklist.
-
If at least one tour matches, continue to "Drift checklist" for that tour.
Drift checklist
For each affected tour, evaluate every item. Skip items that obviously do not apply, but list explicitly which items were checked.
- Orphan selectors — every step's
target(which composes todata-tour-id="<tour-id>-<step.target>") must resolve to a real element in the codebase. Grepui/for the expected attribute value; report any step whose target is missing. - Renamed selectors — a
data-tour-idattribute was edited in this change. Match it back to any tour step referencing the old value. - Outdated copy — a popover
title/descriptionreferences a button label, heading, or term that no longer exists on the covered page. - Obsolete steps — a step describes a section, panel, or workflow that was removed.
- Missing steps — a new feature was added on the covered surface without a corresponding step (e.g. a new panel, a new primary action, a new wizard stage).
- Reordered flow — the user's path through the feature changed (e.g. query builder moved before scan selection) and the step order no longer reflects it.
Version-bump decision tree
Apply per tour after listing drift:
- NO bump when the change is cosmetic. Examples: fix a typo, soften
copy, rename a
data-tour-idselector while keeping the same step, swap one screenshot for another, tighten wording. - BUMP
versionwhen the user-visible flow changes materially. Examples: a new step was added or removed; the order changed; an anchored target was retargeted to a different panel; the tour now covers a new feature on the surface.
What ships with it
3 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.
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.
- 1mo ago First seen · 100 lines · 41 tokens per session scan A 6dbcd5d01661
prowler-tour is a skill published in the GitHub repository prowler-cloud/prowler (15,100 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 973 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 2026-08-30.
Other skills, from other repositories
performing-aws-account-enumeration-with-scout-suite
Perform comprehensive security posture assessment of AWS accounts using ScoutSuite to enumerate resources, identify misconfigurations, and generate actionable security reports.
consensus-safety-invariants
L1 trigger - detects non-determinism, state transition completeness violations, and safety/liveness invariant breaks in consensus code. Inject into depth-consensus-invariant or depth-state-trace.
cross-chain-timing
Trigger Pattern wormhole|layerzero|ccip|bridge|crosschain|vaa|guardian|emitter|relay|remotechain|payload|nonce.sequence - Inject Into Breadth agents, depth-external.
signature-verification-audit
Trigger HASSIGNATURES flag in templaterecommendations.md (recon detects signature verification patterns - see chain-specific grep patterns in TASK 6) - Agent Type general-purp...
object-ownership
Trigger Pattern Always required for Sui Move audits -- object lifecycle and ownership model - Inject Into Breadth agents, depth-state-trace, depth-token-flow.
ability-analysis
Trigger Pattern Always (Aptos Move) - foundational security check - Inject Into Breadth agents, depth agents.