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 j4flmao/agent-skills --skill cloud-security-defensivegit clone --depth 1 https://github.com/j4flmao/agent-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/j4flmao/agent-skills/cloud-security-defensive)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/cloud-security-defensive"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/cloud-security-defensive/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/j4flmao/agent-skills/cloud-security-defensive"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/cloud-security-defensive.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 | $0.00127 | $0.01667 |
| Opus 5.5 | $0.00051 | $0.00667 |
| Sonnet 5.5 | $0.00025 | $0.00333 |
| Haiku 4.5 | $0.00013 | $0.00167 |
Grade A, and why
cloud-native-security-defensive 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 today.
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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Security — Defensive Engineering
Purpose
Turn a cloud estate into one where dangerous actions are prevented by organization-level guardrails, everything else is logged centrally and immutably, and anomalous identity activity is detected quickly. Identity is the perimeter in cloud, so most controls are IAM controls.
Agent Protocol
Trigger
"harden aws account", "detect cloud intrusion", "cloudtrail", "SCP", "guardrails", "secure azure tenant", "cloud posture", "guardduty", "IMDSv2", "least privilege".
Input Context
- Cloud(s) and org structure (AWS Organizations OUs, Azure management groups, GCP folders).
- Existing logging destinations (SIEM, log archive account).
- Compliance targets (CIS Benchmarks, SOC 2, ISO 27001).
Output Artifact
Policy-as-code (SCP/Azure Policy/Org Policy JSON or Terraform) and detection queries. No file unless requested.
Response Format
Layer: {preventive|detective|responsive}
Control: {name}
Scope: {org/OU/account/subscription/project}
Code: {policy or query}
Break-glass impact: {who is exempt and how}
Completion Criteria
- Preventive guardrails applied at org/OU level with a documented break-glass exemption.
- Org-wide audit logging to a separate, write-protected account/project.
- Detections mapped to concrete log events.
Control Layers
| Layer | AWS | Azure | GCP |
|---|---|---|---|
| Org guardrails | Service Control Policies, Resource Control Policies, declarative policies | Azure Policy (deny), management-group RBAC | Organization Policy constraints |
| Audit log | CloudTrail organization trail (+ data events where needed) | Activity Log + Microsoft Entra sign-in/audit logs via diagnostic settings | Cloud Audit Logs (Admin Activity always on; Data Access opt-in) |
| Threat detection | GuardDuty, Security Hub | Microsoft Defender for Cloud, Sentinel | Security Command Center |
| Unused access | IAM Access Analyzer (unused access findings) | Entra access reviews | IAM Recommender |
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.
- today Changed · +99 lines · +127 tokens per session a11b58e04125
- 1mo ago First seen · 32 lines · 0 tokens per session scan A f4a9fcb44fde
cloud-native-security-defensive is a skill published in the GitHub repository j4flmao/agent-skills (34 stars, last pushed today), licensed MIT. It adds 127 tokens to every session and 1,667 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
cloud-iam-deep
GCP/AWS/Azure cloud exploitation -- Cloud Functions, Firestore, Cloud Run, S3, MinIO, Blob Storage, SA keys.
deploying-cloud-deception-with-decoy-resources
Deploy cloud-native deception across AWS, Azure, and GCP using decoy (honey) resources whose only purpose is to generate a high-fidelity alert the instant an attacker touches them: canary IAM access keys, permission-less decoy users/roles/service principals, honey object-storage buckets, and decoy secrets in Secrets…
conducting-cloud-infrastructure-penetration-test
Perform a cloud infrastructure penetration test across AWS, Azure, and GCP to identify IAM misconfigurations, exposed storage buckets, insecure serverless functions, and cloud-native attack paths using Pacu, ScoutSuite, and Prowler.
conducting-cloud-infrastructure-penetration-test
Perform a cloud infrastructure penetration test across AWS, Azure, and GCP to identify IAM misconfigurations, exposed storage buckets, insecure serverless functions, and cloud-native attack paths using Pacu, ScoutSuite, and Prowler.
ovh
OVHcloud infrastructure integration for managing instances, Kubernetes clusters, networks, and object storage via CLI and Terraform.
scaleway
Scaleway cloud integration for managing instances, Kapsule Kubernetes clusters, object storage, and managed databases via CLI and Terraform.