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 Kin9Zeus/senior-engineer-skills --skill cloud-securitygit clone --depth 1 https://github.com/Kin9Zeus/senior-engineer-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/kin9zeus/senior-engineer-skills/cloud-security)<a href="https://agentmods.dev/skills/kin9zeus/senior-engineer-skills/cloud-security"><img src="https://agentmods.dev/badge/skills/kin9zeus/senior-engineer-skills/cloud-security/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/kin9zeus/senior-engineer-skills/cloud-security"><img src="https://agentmods.dev/badge/skills/kin9zeus/senior-engineer-skills/cloud-security.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 | $0.00232 | $0.02340 |
| Opus 5.5 | $0.00093 | $0.00936 |
| Sonnet 5.5 | $0.00046 | $0.00468 |
| Haiku 4.5 | $0.00023 | $0.00234 |
Grade A, and why
cloud-security 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 2d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Security
Every platform you depend on is somebody else's code and somebody else's employees. Hosts get breached, CI tokens leak, and a vendor's "limited subset" turns out to include you. You cannot prevent that. You can decide, in advance, how much a stolen secret is worth.
The design goal: an attacker who obtains everything your platform stores — every environment variable, every token — should find credentials that are narrow, short-lived, network-restricted, spend-capped, and detected on first use.
Scope: infrastructure the user owns or is authorised to assess. Review is read-only by default; changes to live infrastructure need the user's confirmation. No probing of provider infrastructure or other tenants.
1 · The order of work
1 INVENTORY every secret, every identity, every internet-facing thing
2 SECRETS climb the ladder (below): fewer, narrower, shorter-lived
3 IDENTITY least privilege; no shared keys; MFA; federated CI
4 NETWORK private by default; data stores unreachable from the internet; egress control
5 RUNTIME patched, minimal, non-root, read-only, resource-limited
6 DATA encrypted, backed up, restore-tested, retention-bounded
7 DETECTION audit logs on and watched; canaries; alert on the dangerous few
8 REPEATABLE infrastructure as code, scanned; rotation drill rehearsed
Do steps 1–3 first. They are where a platform breach turns from an incident into a catastrophe or into an afternoon.
2 · The secrets ladder
Where a secret lives decides what a breach of that place costs. Climb as high as the platform allows.
| Rung | Where | What a breach gives the attacker |
|---|---|---|
| 0 | Hard-coded in source | Everything, forever, in every clone |
| 1 | .env committed or shared in chat |
Same, plus your history |
| 2 | Plain platform environment variables | Everything the platform stored — this is what a platform-store breach exposes |
| 3 | Write-only / "sealed" platform variables | Better against UI/API read-back; a breach of the storage layer itself may still expose them — ask the provider, do not assume |
| 4 | Dedicated secrets manager, fetched at runtime with the workload's identity | Attacker needs the identity and a network path; access is logged and revocable centrally |
| 5 | No static secret: federated, short-lived credentials (OIDC / workload identity) | A stolen token expires in minutes; nothing to rotate |
What ships with it
2 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.
- 2d ago First seen · 184 lines · 232 tokens per session scan A 78484c76cd5c
cloud-security is a skill published in the GitHub repository Kin9Zeus/senior-engineer-skills (3 stars, last pushed 2d ago), licensed MIT. It adds 232 tokens to every session and 2,340 once invoked, about $0.0009 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 2026-10-24.
Other skills, from other repositories
kubernetes-specialist
Use when deploying or managing Kubernetes workloads. Invoke to create deployment manifests, configure pod security policies, set up service accounts, define network isolation rules, debug pod crashes, analyze resource limits, inspect container logs, or right-size workloads. Use for Helm charts, RBAC policies…
offensive-container-escape
Container escape and breakout techniques targeting Docker, containerd, and Podman runtimes. Covers privileged container breakout via host filesystem mount and nsenter, Docker socket abuse through /var/run/docker.sock, Linux capability exploitation including CAPSYSADMIN, CAPSYSPTRACE, and CAPNETADMIN, cgroup v1…
ecs
AWS ECS container orchestration for running Docker containers. Use when deploying containerized applications, configuring task definitions, setting up services, managing clusters, or troubleshooting container issues.
eks
AWS EKS Kubernetes management for clusters, node groups, and workloads. Use when creating clusters, configuring IRSA, managing node groups, deploying applications, or integrating with AWS services.
agents-v2-py
Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry.
kubernetes
Expert in Kubernetes and DevOps with infrastructure-as-code and cloud-native patterns.