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 eveld/claude --skill gcp-awarenessgit clone --depth 1 https://github.com/eveld/claudeWrote 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/eveld/claude/gcp-awareness)<a href="https://agentmods.dev/skills/eveld/claude/gcp-awareness"><img src="https://agentmods.dev/badge/skills/eveld/claude/gcp-awareness/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/eveld/claude/gcp-awareness"><img src="https://agentmods.dev/badge/skills/eveld/claude/gcp-awareness.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 | $0.00022 | $0.00705 |
| Opus 5 | $0.00011 | $0.00352 |
| Sonnet 5 | $0.00004 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
gcp-awareness 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 10d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GCP Skills Guide
You have specialized GCP debugging skills. Use these instead of raw gcloud commands for consistent, well-documented workflows.
Decision Tree
Skills vs Agents
Simple, single gcloud command query?
→ Use gcp-logs skill
- Better than: Running raw
gcloud logging readcommands - Example: "Find ERROR logs for api-gateway service"
- Use when: Quick log fetch, single service, no correlation needed
Complex investigation requiring multiple steps? → Use Task tool with GCP agents (conserves context)
gcp-locator- Fetch logs from multiple services, save to /tmpgcp-analyzer- Filter logs, diagnose service issues, check IAMgcp-pattern-finder- Correlate logs across services, build timelines- Use when: Multi-service investigation, correlation, pattern detection
When to Use Which Agent
Just need to fetch logs broadly?
→ Use gcp-locator agent only
- Fetches logs from multiple services/time ranges
- Saves to /tmp for later analysis
- Example: "Get all ERROR logs from service-b, service-a, backend for last hour"
Investigating single service issue?
→ Use gcp-locator + gcp-analyzer agents
- Locator: Fetch relevant logs
- Analyzer: Filter, diagnose root cause, check IAM/roles
- Example: "Debug service-b permission errors"
Need to correlate across services or find patterns?
→ Use all three: gcp-locator + gcp-analyzer + gcp-pattern-finder
- Locator: Fetch from all relevant services
- Analyzer: Filter each service's logs
- Pattern-finder: Correlate by trace_id, build timelines, find patterns
- Example: "Trace request flow across service-a → service-b → backend"
Need to understand GCP IAP authentication? → Check documentation or use WebFetch
- GCP IAP tokens:
gcloud auth print-identity-token - Use for Grafana, ArgoCD, Temporal access
Available GCP Tools
| Type | Name | Purpose |
|---|---|---|
| Skill | gcp-logs | Simple log queries (single gcloud command) |
| Agent | gcp-locator | Fetch logs from multiple services/ranges |
| Agent | gcp-analyzer | Analyze service logs, diagnose issues |
| Agent | gcp-pattern-finder | Correlate logs, find patterns, build timelines |
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.
- 10d ago First seen · 84 lines · 22 tokens per session scan A 90ee5c49fe9e
gcp-awareness is a skill published in the GitHub repository eveld/claude (10 stars, last pushed 7mo ago), licensed MIT. It adds 22 tokens to every session and 705 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 2026-08-31.
Other skills, from other repositories
event-driven-architecture
Kafka, RabbitMQ, SQS/SNS, event sourcing, CQRS, saga patterns, dead letter queues, and idempotency. Use when designing asynchronous systems, implementing message-driven workflows, or building event streaming pipelines.
cloudflare-workers-publish
Deploy static HTML files to Cloudflare Workers with 1Password credential management.
devops-cloud
DevOps, cloud infrastructure, and platform engineering. Use when working with AWS, GCP, Azure, Kubernetes, Terraform, CI/CD pipelines, or infrastructure as code.
doppler-workflows
Manage credentials and secrets through Doppler for publishing and deployment workflows. Use whenever the user needs to publish Python packages.
edge-computing
Edge computing with Cloudflare Workers, Deno Deploy, Bun, Vercel Edge Functions, AWS Lambda@Edge, and edge databases (Turso, D1, DynamoDB Global Tables). Use when building low-latency edge applications, edge-side rendering, or globally distributed compute.
dell-idrac-bmc-ops
Bring a Dell PowerEdge BMC (iDRAC) onto the network headlessly, standardize its baseline settings, stage its firmware, and drive an unattended Proxmox/Linux install through it — including generation-specific Redfish/racadm gotchas, the identity-before-power-action rule, and the phantom-drive failure mode caused by…