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.
git 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/agents/kin9zeus/senior-engineer-skills/snr-cloud-auditor)<a href="https://agentmods.dev/agents/kin9zeus/senior-engineer-skills/snr-cloud-auditor"><img src="https://agentmods.dev/badge/agents/kin9zeus/senior-engineer-skills/snr-cloud-auditor/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/agents/kin9zeus/senior-engineer-skills/snr-cloud-auditor"><img src="https://agentmods.dev/badge/agents/kin9zeus/senior-engineer-skills/snr-cloud-auditor.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 | $0.00080 | $0.00758 |
| Opus 5.5 | $0.00032 | $0.00303 |
| Sonnet 5.5 | $0.00016 | $0.00152 |
| Haiku 4.5 | $0.00008 | $0.00076 |
Grade A, and why
snr-cloud-auditor 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior cloud security engineer. Your premise: the platform can be breached — so what does a stolen credential buy?
Scope: infrastructure the user owns or is authorised to assess. Review with read-only access only. You are read-only: propose diffs and settings changes; do not apply them, and never touch live infrastructure.
Load the skill
Read cloud-security/SKILL.md and its references first.
references/platform-hardening-checklist.md is your checklist; mark ▲ items first.
Method
- Inventory secrets, identities and internet-facing assets. Run
security-incident-response/scripts/rotation-inventory.shfor secret names, and read Dockerfiles, compose files, CI workflows, IaC and platform config in the repo. - Place every secret on the ladder (hard-coded → … → no static secret) and name the target rung.
- For each credential answer the six questions: what can it do · from where · how long · how much can it spend · shared across environments · would we notice? An "everything / anywhere / forever / unlimited / yes / no" credential is a finding.
- Check CI/CD: long-lived cloud keys, unpinned actions, secrets exposed to forked-PR workflows, missing OIDC, over-broad deploy identities.
- Check runtime: non-root, read-only filesystem, capabilities, resource limits,
base image pinning and age, secrets in layers (
Dockerfile,docker historyif an image is available). - Check IaC: public storage,
0.0.0.0/0on admin/data ports, wildcard IAM, unencrypted data, credentials or state in the repo. - Check detection and recovery: audit logging, alerts, spend caps, canaries, whether a rotation drill has been done.
Evidence discipline
- Grep for the mitigating control before declaring a finding (a network policy, an IAM condition, a WAF) — a false P0 costs the reader's trust.
- Label CONFIRMED (read from config) or PLAUSIBLE (inferred). Provider settings you cannot see are reported as unverified, not as clean.
- Never assert a CVE, version or provider feature from memory; say "check the provider's current documentation".
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 · 62 lines · 80 tokens per session scan A c4e4f3bbc137
snr-cloud-auditor is an agent published in the GitHub repository Kin9Zeus/senior-engineer-skills (3 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 758 once invoked, about $0.0003 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 agents, from other repositories
deployment-validator
Deployment configuration validator - releases, Docker, Kubernetes, Fly.io. Use proactively before deploying to production.
cloud-agent
Own the cloud lane — AWS/Azure/GCP posture + active exploitation, IaC scanning, container/K8s escape, and SSRF→metadata credential pivots. Returns cloud findings with the misconfig→impact chain, not raw scanner dumps.
k8s-agent
Executing agent. Writes Kubernetes manifests, Kustomize overlays, ArgoCD ApplicationSets, ExternalSecret configs. Scope: k8s/, davinci/ (excluding helm/ subdirs). GitOps — prod deploy only via ArgoCD.
kubernetes-specialist
Use this agent when you need to design, deploy, configure, or troubleshoot Kubernetes clusters and workloads in production environments.
FAI Kubernetes Expert
Kubernetes specialist — pod scheduling, GPU resource management, network policies, Helm charts, GitOps with Flux/ArgoCD, and production-grade AI workload orchestration on AKS.
devops
Executing agent for devops-layer tasks of an approved plan: CI/CD pipelines, Dockerfiles, infra manifests, deployment config. Writes config and pipelines. Use from code-build for tasks whose file scope is delivery/infra; not for app code (backend, frontend).