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 agentmods add skills/unitoneai/securityskills/cloud-security-engineernpx skills add UnitOneAI/SecuritySkills --skill cloud-security-engineergit clone --depth 1 https://github.com/UnitOneAI/SecuritySkillsWhat 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 | $0.00079 | $0.04598 |
| Opus 5 | $0.00039 | $0.02299 |
| Sonnet 5 | $0.00016 | $0.00920 |
| Haiku 4.5 | $0.00008 | $0.00460 |
Grade A, and why
cloud-security-engineer 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 yesterday.
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 — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Security Engineer Role Bundle
A structured cloud security guide for engineers who own the security posture of cloud environments across AWS, Azure, and GCP. This bundle replaces ad-hoc cloud configuration reviews with repeatable engagement patterns that produce hardened environments, least-privilege identity configurations, and infrastructure-as-code security baselines.
When to Use
Invoke this role bundle when any of the following conditions are true:
- Cloud posture review needed. A cloud environment (AWS account, Azure subscription, GCP project) needs a security assessment — either a new environment before workloads are deployed or an existing environment that has never been formally reviewed.
- IaC security review. Terraform, CloudFormation, Bicep, or Pulumi templates need security validation before being applied to production infrastructure.
- Container orchestrator hardening. Kubernetes (EKS, AKS, GKE) or other container orchestration platforms need security configuration review — RBAC, network policies, pod security, and workload identity.
- Identity governance assessment. IAM policies, roles, service accounts, and cross-account/cross-project trust relationships need review for least privilege, unused access, and privilege escalation paths.
- Zero trust program. The organization is implementing zero trust architecture and needs to assess current posture, define target architecture, and build the implementation roadmap.
If the ask is about application-layer security (e.g., "review this API for BOLA"), use the appsec-engineer role bundle. If the ask is about overall security program maturity, use the vciso role bundle. This bundle is for cloud infrastructure security.
Skills: All skills referenced in this bundle are available: iam-review, threat-modeling, pipeline-security, aws-review, azure-review, gcp-review, container-security, iac-security, zero-trust-assessment, segmentation, privileged-access.
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.
- yesterday First seen · 363 lines · 79 tokens per session scan A 127c5228aa29
cloud-security-engineer is a skill published in the GitHub repository UnitOneAI/SecuritySkills (56 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 4,598 once invoked, about $0.0004 per session on Opus 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
speckit-implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit-clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
speckit-plan
Execute the implementation planning workflow using the plan template to generate design artifacts.
speckit-specify
Create or update the feature specification from a natural language feature description.
speckit-tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
speckit-taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.