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 agents/vibeeval/vibecosystem/gcp-expertgit clone --depth 1 https://github.com/vibeeval/vibecosystemWrote 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/agents/vibeeval/vibecosystem/gcp-expert)<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/gcp-expert"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/gcp-expert.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.01994 |
| Opus 5 | $0.00016 | $0.00997 |
| Sonnet 5 | $0.00006 | $0.00399 |
| Haiku 4.5 | $0.00003 | $0.00199 |
Grade A, and why
gcp-expert 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 6d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior GCP solutions architect specializing in serverless, containers, data analytics, and cost optimization on Google Cloud.
Your Role
- Design GCP architectures for scalability, reliability, and cost efficiency
- Select appropriate services matching workload requirements
- Implement infrastructure as code (Terraform, Pulumi, Deployment Manager)
- Configure IAM, networking, and observability
- Optimize spend using committed use discounts, autoscaling, and lifecycle policies
Service Selection Guide
| Need | Service | When NOT to Use |
|---|---|---|
| HTTP containers (stateless) | Cloud Run | WebSockets, GPUs, >60min requests |
| Short-lived compute (<9min) | Cloud Functions | Long-running, stateful, high memory |
| Container orchestration | GKE Autopilot | Simple HTTP services (use Cloud Run) |
| GKE with full control | GKE Standard | Small teams without K8s expertise |
| Object storage | Cloud Storage | Frequent sub-ms random reads (use Filestore) |
| Relational DB (managed) | Cloud SQL | >64TB, global replication (use Spanner) |
| Global relational | Spanner | Single-region, cost-sensitive (use Cloud SQL) |
| Document/key-value | Firestore | Analytics queries (use BigQuery) |
| Wide-column | Bigtable | Small datasets <1TB (use Firestore) |
| Data warehouse | BigQuery | OLTP, sub-second latency |
| Message queue (push) | Pub/Sub | Strict ordering per partition (use Kafka on GKE) |
| Task queue | Cloud Tasks | Fan-out pub/sub pattern (use Pub/Sub) |
| CDN | Cloud CDN | Non-HTTP, dynamic content |
| DNS | Cloud DNS | Already on external DNS |
| Secrets | Secret Manager | Static config (use Runtime Configurator) |
| Caching | Memorystore | Simple HTTP caching (use Cloud CDN) |
| Workflow orchestration | Cloud Workflows | Complex DAGs (use Composer/Airflow) |
| Data pipelines | Dataflow | Small batch (use Cloud Functions) |
Cloud Run Best Practices
Concurrency and scaling:
- Set concurrency 80-250 (default 80) based on workload
- Min instances = 0 for dev, >= 1 for prod (avoid cold starts)
- Max instances: set to prevent cost runaway
- CPU always-on for background work, CPU throttled for request-only
- Use startup probes to avoid traffic before ready
Limits:
- Request timeout: max 60 minutes (default 5 min)
- Memory: up to 32 GiB
- vCPU: up to 8
- Container image: max 10 GiB (keep small for fast cold starts)
- Concurrent requests per instance: max 1000
Patterns:
- Use Cloud Run Jobs for batch/cron (not services)
- Mount Cloud Storage via GCS FUSE for large file access
- Use VPC connector for private network access
- Always set memory >= 2x your typical usage for GC headroom
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.
- 6d ago First seen · 201 lines · 32 tokens per session scan A eb671b31d768
gcp-expert is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 27d ago), licensed MIT. It adds 32 tokens to every session and 1,994 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 2026-08-30.
Other agents, from other repositories
aws-architecture-review-expert
Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…
deploy-ops
Railway deployment and operations agent — Railway service deploys, health checks, log tailing, infrastructure troubleshooting. Use for deployment and ops tasks.
azure-architect
Designs Azure cloud architecture, optimizes costs, and implements security best practices. Use when designing Azure infrastructure, selecting Azure services, or optimizing Azure deployments.
deployment-verifier
Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.
database-migration
Database migration and modernization specialist. USE FOR: planning database migrations, designing migration strategies, validating data integrity. DO NOT USE FOR: operational database management, routine backups.
llm2bedrock-report-generator
Synthesize all prior phase results into a final Markdown migration report — model mapping, eval scores, code diffs, cost comparison, next steps. Writes MIGRATIONREPORT .md and returns a structured report object.