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 selvarajmurugesan90/ops-engineering-skills --skill cloud-iam-hardeninggit clone --depth 1 https://github.com/selvarajmurugesan90/ops-engineering-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/selvarajmurugesan90/ops-engineering-skills/cloud-iam-hardening)<a href="https://agentmods.dev/skills/selvarajmurugesan90/ops-engineering-skills/cloud-iam-hardening"><img src="https://agentmods.dev/badge/skills/selvarajmurugesan90/ops-engineering-skills/cloud-iam-hardening/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/selvarajmurugesan90/ops-engineering-skills/cloud-iam-hardening"><img src="https://agentmods.dev/badge/skills/selvarajmurugesan90/ops-engineering-skills/cloud-iam-hardening.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 | $0.00115 | $0.02914 |
| Opus 5.5 | $0.00046 | $0.01166 |
| Sonnet 5.5 | $0.00023 | $0.00583 |
| Haiku 4.5 | $0.00012 | $0.00291 |
Grade A, and why
cloud-iam-hardening 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud IAM Hardening
Purpose
Identity is the perimeter in cloud environments — network controls help, but the vast majority of real-world cloud breaches trace back to over-permissioned roles, leaked long-lived credentials, or a human/service account with far more access than its job requires. IAM hardening is not a one-time setup step; it is a continuous discipline of shrinking permissions to what's actually used, replacing static credentials with short-lived federated tokens, and reviewing access on a cadence. This skill applies across AWS IAM, Azure RBAC/Entra ID, and GCP IAM, since the underlying failure modes (privilege creep, standing admin access, long-lived keys) are identical even though the primitives differ.
When to use
- Reducing an over-broad policy (e.g.
AdministratorAccess,Owner,roles/editor) down to least privilege for a specific workload or team. - Setting up CI/CD pipelines (GitHub Actions, GitLab CI, Azure DevOps) to authenticate to cloud APIs without storing static access keys/service account keys as secrets.
- Investigating "who can do X" or "why does this role have this permission" during an incident or audit.
- Implementing break-glass emergency access that bypasses normal SSO/MFA flows only when genuinely needed, with full audit logging.
- Running a quarterly or post-incident access review to find unused permissions, stale credentials, or orphaned service principals.
- Responding to a cloud security posture finding like "N IAM users have console access keys older than 90 days" or "M service accounts have organization-level Owner."
Prerequisites & environment
- Read access to the relevant IAM surface: AWS IAM Access Analyzer / CloudTrail, Azure AD sign-in + audit logs / Entra Permissions Management, or GCP IAM Recommender / Policy Analyzer — these tools generate the "what's actually used" data that least-privilege redesigns depend on; don't guess permissions from documentation alone.
- For CI/CD federation: the CI platform must support OIDC token issuance (GitHub Actions, GitLab CI ≥ 15.7, CircleCI, Azure DevOps all do natively as of 2024).
- Terraform ≥ 1.5 (or the cloud-native IaC of choice) if policies are managed as code — strongly recommended over console-managed IAM once past a handful of roles.
- Organizational agreement on a break-glass process owner and an alerting destination (e.g. a PagerDuty escalation) before implementing break-glass access, so its use is always followed up on.
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 · 257 lines · 115 tokens per session scan A a26ef90e887d
cloud-iam-hardening is a skill published in the GitHub repository selvarajmurugesan90/ops-engineering-skills (42 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 115 tokens to every session and 2,914 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 2026-08-30.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running security audits (auditcluster.sh), enforcing Network Policies (default-deny and Dataplane V2 logging), isolating high-risk pods inside GKE Sandbox (gVisor), enforcing Pod…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for generating K8s YAML manifests (use gke-manifest-generation) or disaster recovery…
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".