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 niels-emmer/myace --skill gcp-security-checklistgit clone --depth 1 https://github.com/niels-emmer/myaceWrote 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/niels-emmer/myace/gcp-security-checklist)<a href="https://agentmods.dev/skills/niels-emmer/myace/gcp-security-checklist"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/gcp-security-checklist/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/niels-emmer/myace/gcp-security-checklist"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/gcp-security-checklist.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 | $0.00040 | $0.00825 |
| Opus 5 | $0.00020 | $0.00413 |
| Sonnet 5 | $0.00008 | $0.00165 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
GCP Security Checklist 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
A fast, consistent pass over a GCP infrastructure change to catch the
GCP-recommended security-practice violations that are easy to miss in a large
plan or diff — before it ever reaches the point of asking a human to approve
an apply. This is the GCP-specific companion to iac-expert's generic
iac-security-checklist, adding the GCP constructs (IAM, service accounts,
VPC firewall rules, Cloud KMS, Secret Manager, Security Command Center, Cloud
Audit Logs) that the generic checklist can't name.
When to use it
Run this against every nontrivial GCP change (new resources, modified network/identity/access configuration) before handing it off for review or requesting apply approval. For a trivial change (a label fix, a variable rename with no resource impact), a quick skim is enough.
Checklist
Mark each item PASS, FAIL, or N/A. Every FAIL needs either a fix or a
documented exception (see iac-expert's exception-documentation skill)
before the change moves forward.
Identity and access
- Service-to-service and CI/CD auth uses service accounts and Workload Identity Federation, not long-lived service-account keys.
- Any IAM role is scoped to least privilege (specific permissions/
resources, not
roles/owner/*) and uses Google-managed (predefined) roles where possible. - Human access is behind IAM with MFA — no shared accounts, no standing service-account keys in code or config.
- Secrets that must exist live in Secret Manager, referenced by ID —
never embedded as a literal in
.tf, a tfvars file, or a module default.
Network
- No resource has a public IP, public endpoint, or
0.0.0.0/0-equivalent VPC firewall rule unless it's a documented exception. - Workloads run in private networking; Google-managed services are reached via Private Service Connect (or VPC peering) where supported, keeping traffic off the public internet.
- Inter-service traffic that could stay on a private VPC does; VPC firewall rules default to deny and open only what's needed.
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.
- 9d ago First seen · 80 lines · 40 tokens per session scan A b3bb86fac888
GCP Security Checklist is a skill published in the GitHub repository niels-emmer/myace (1 stars, last pushed 5d ago), licensed MIT. It adds 40 tokens to every session and 825 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
implementing-gcp-organization-policy-constraints
Implement GCP Organization Policy constraints to enforce security guardrails across the entire resource hierarchy, restricting risky configurations and ensuring compliance at organization, folder, and project levels.
Cloud Security & Container Hardening
AWS/Azure/GCP security auditing, container and Kubernetes hardening, Infrastructure as Code scanning, and cloud compliance assessment.
loom-kubernetes
Kubernetes deployment, cluster architecture, security, and operations.
loom-prometheus
Prometheus monitoring and alerting for cloud-native observability.
loom-terraform
Infrastructure as Code with Terraform/OpenTofu.
loom-karpenter
Kubernetes node autoscaling and cost optimization with Karpenter.