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 khalilbenaz/claude-skills-collection --skill gcp-guidegit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/khalilbenaz/claude-skills-collection/gcp-guide)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/gcp-guide"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/gcp-guide/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/khalilbenaz/claude-skills-collection/gcp-guide"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/gcp-guide.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 | $0.00065 | $0.02018 |
| Opus 5 | $0.00032 | $0.01009 |
| Sonnet 5 | $0.00013 | $0.00404 |
| Haiku 4.5 | $0.00006 | $0.00202 |
Grade A, and why
gcp-guide 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GCP Guide
Workflow
1. Structurer la hiérarchie des ressources
Organization
└── Folder (prod / staging / dev)
└── Project (une app ou un domaine)
└── Resources (Cloud Run, BigQuery, etc.)
- Crée un projet distinct par environnement ; jamais partager des projets entre prod et non-prod.
- Attribue un budget + alerte à chaque projet dès la création.
gcloud projects create my-app-prod --folder=FOLDER_ID
gcloud billing projects link my-app-prod --billing-account=BILLING_ID
gcloud alpha billing budgets create \
--billing-account=BILLING_ID \
--display-name="my-app-prod budget" \
--budget-amount=500USD \
--threshold-rule=percent=0.8
2. IAM — moindre privilège dès le départ
- Un service account par workload, jamais la clé par défaut Compute.
- Préfère Workload Identity Federation (pas de clé JSON) pour les pipelines CI/CD.
- Rôles custom > rôles primitifs (Owner/Editor/Viewer).
# Créer un SA dédié
gcloud iam service-accounts create sa-cloud-run-api \
--display-name="API Cloud Run"
# Binding minimal
gcloud projects add-iam-policy-binding PROJECT_ID \
--member="serviceAccount:sa-cloud-run-api@PROJECT_ID.iam.gserviceaccount.com" \
--role="roles/run.invoker"
3. Choisir le bon service de calcul
| Besoin | Service recommandé |
|---|---|
| API HTTP / microservice conteneurisé, trafic variable | Cloud Run |
| Workloads Kubernetes existants, GPU, état local | GKE Autopilot |
| Traitement event-driven simple (<10 min) | Cloud Functions 2nd gen |
| Batch HPC ou ML training | Batch + GPU/TPU |
| VM legacy ou contrôle OS total | Compute Engine |
# Déployer sur Cloud Run depuis une image Artifact Registry
gcloud run deploy my-api \
--image=europe-west1-docker.pkg.dev/PROJECT_ID/repo/my-api:latest \
--region=europe-west1 \
--platform=managed \
--service-account=sa-cloud-run-api@PROJECT_ID.iam.gserviceaccount.com \
--min-instances=0 \
--max-instances=20 \
--concurrency=80 \
--no-allow-unauthenticated
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 · 221 lines · 65 tokens per session scan A 87f7fb664232
gcp-guide is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 19d ago), licensed MIT. It adds 65 tokens to every session and 2,018 once invoked, about $0.0003 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
n8n-workflow
Build n8n automation workflows — nodes, expressions, error handling, and self-hosted deployment.
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.
api-patterns
API design: naming, versioning, pagination, idempotency, OpenAPI, error contracts and safe retries. Triggers: API design, REST, GraphQL, OpenAPI, Swagger, error response, HTTP status, rate limit.
csharp-patterns
C#/.NET: LINQ, async/await, DI, records, nullable refs, ASP.NET Core, EF Core, MediatR. Triggers: C#, .NET, dotnet, ASP.NET, EF Core, LINQ, record type, IServiceCollection.
java-patterns
Java: Spring Boot, CompletableFuture, records, sealed types, JPA/Hibernate, virtual threads. Triggers: Java, Spring, JPA, Hibernate, Maven, Gradle, virtual thread, sealed class.
rollback
Rolls back git commit, DB migration, or deploy to known-good with safety + health checks. Triggers: rollback, revert deploy, revert migration, rollback commit, git revert.