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 faberlens/hardened-skills --skill gcp-cli-hardenedgit clone --depth 1 https://github.com/faberlens/hardened-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/faberlens/hardened-skills/gcp-cli-hardened)<a href="https://agentmods.dev/skills/faberlens/hardened-skills/gcp-cli-hardened"><img src="https://agentmods.dev/badge/skills/faberlens/hardened-skills/gcp-cli-hardened/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/faberlens/hardened-skills/gcp-cli-hardened"><img src="https://agentmods.dev/badge/skills/faberlens/hardened-skills/gcp-cli-hardened.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 | $0.00020 | $0.01046 |
| Opus 5 | $0.00010 | $0.00523 |
| Sonnet 5 | $0.00004 | $0.00209 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
Google Cloud-hardened 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 8d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Cloud Production Rules
Cost Traps
- Stopped Compute Engine VMs still pay for persistent disks and static IPs — delete disks or use snapshots for long-term storage
- Cloud NAT charges per VM and per GB processed — use Private Google Access for GCP API traffic instead
- BigQuery on-demand pricing charges for bytes scanned, not rows returned — partition tables and use
LIMITin dev, butLIMITdoesn't reduce scan cost in prod - Preemptible VMs save 80% but can be terminated anytime — only for fault-tolerant batch workloads
- Egress to internet costs, egress to same region is free — keep resources in same region, use Cloud CDN for global distribution
Security Rules
- Service accounts are both identity and resource — one service account can impersonate another with
roles/iam.serviceAccountTokenCreator - IAM policy inheritance: Organization → Folder → Project → Resource — deny policies at org level override allows below
- VPC Service Controls protect against data exfiltration — but break Cloud Console access if not configured with access levels
- Default Compute Engine service account has Editor role — create dedicated service accounts with least privilege
- Workload Identity Federation eliminates service account keys — use for GitHub Actions, GitLab CI, external workloads
Networking
- VPC is global, subnets are regional — unlike AWS, single VPC can span all regions
- Firewall rules are allow-only by default — implicit deny all ingress, allow all egress. Add explicit deny rules for egress control
- Private Google Access is per-subnet setting — enable on every subnet that needs to reach GCP APIs without public IP
- Cloud Load Balancer global vs regional — global for multi-region, but regional is simpler and cheaper for single region
- Shared VPC separates network admin from project admin — host project owns network, service projects consume it
Performance
- Cloud Functions gen1 has 9-minute timeout — gen2 (Cloud Run based) allows 60 minutes
- Cloud SQL connection limits vary by instance size — use connection pooling or Cloud SQL Auth Proxy
- Firestore/Datastore hotspotting on sequential IDs — use UUIDs or reverse timestamps for document IDs
- GKE Autopilot simplifies but limits — no DaemonSets, no privileged containers, no host network
- Cloud Storage single object limit is 5TB — use compose for larger, parallel uploads for faster
What ships with it
1 file 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.
- 8d ago First seen · 65 lines · 20 tokens per session scan A 48770fb7fe80
Google Cloud-hardened is a skill published in the GitHub repository faberlens/hardened-skills (23 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 1,046 once invoked, about $0.0001 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
model-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…
cloud-iam-deep
Cloud IAM red-team attack chain across AWS, Azure, GCP — focused on EXTERNAL exploitation paths and post-credential-discovery privilege analysis. Covers IAM enumeration (aws iam, az role, gcloud iam), STS/AssumeRole chaining, Azure Managed Identity abuse (via SSRF/leak), GCP service account JSON abuse, IMDSv1/v2…
risk-metrics-calculation
Calculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk, implementing risk limits, or building risk monitoring systems.
employment-contract-templates
Create employment contracts, offer letters, and HR policy documents following legal best practices. Use when drafting employment agreements, creating HR policies, or standardizing employment documentation.
calendar
Calendar and scheduling management. Use this skill when the user needs to create, view, update, or manage calendar events, appointments, meetings, or schedule-related tasks. Supports ICS file format, recurring events, and timezone handling.
rag-implementation
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.