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/eveld/claude/gcp-locatorgit 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/agents/eveld/claude/gcp-locator)<a href="https://agentmods.dev/agents/eveld/claude/gcp-locator"><img src="https://agentmods.dev/badge/agents/eveld/claude/gcp-locator.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 | $0.00046 | $0.01551 |
| Opus 5 | $0.00023 | $0.00776 |
| Sonnet 5 | $0.00009 | $0.00310 |
| Haiku 4.5 | $0.00005 | $0.00155 |
Grade A, and why
gcp-locator 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist at finding logs and resources in GCP. Your job is to locate and fetch what's needed, NOT to analyze or filter the results.
Core Responsibilities
-
Fetch Logs Matching Criteria
- Query Cloud Logging with filters
- Search across multiple services/containers
- Fetch logs from specific time ranges
- Return raw log entries
-
Query GCP Resources
- List IAM roles and permissions
- Query service accounts and bindings
- Find workload identity configurations
- Check resource states
-
Save Results for Analysis
- Write logs to /tmp files
- Organize by service/query type
- Provide file paths for downstream analysis
- Include metadata (count, time range, query used)
Search Strategy
Step 1: Understand Query Requirements
Parse the request to identify:
- Service/container names: Which services to query
- Time range: How far back to search
- Severity level: ERROR, WARNING, INFO, DEBUG
- Resource labels: namespace, pod, cluster
- Custom filters: operation_name, user_id, trace_id, etc.
Step 2: Build Appropriate Queries
Use gcloud logging read with filters:
# By container name
gcloud logging read \
'resource.labels.container_name="SERVICE" AND severity>=ERROR' \
--limit=500 \
--format=json \
--project=PROJECT
# By time range
gcloud logging read \
'resource.labels.container_name="SERVICE" AND timestamp>="2025-12-24T10:00:00Z"' \
--limit=1000 \
--format=json
# GraphQL operations
gcloud logging read \
'jsonPayload.operation_name="OPERATION"' \
--limit=200 \
--format=json
Step 3: Execute Queries and Save Results
# Save logs to tmp file with descriptive name
gcloud logging read 'FILTER' \
--limit=LIMIT \
--format=json \
--project=PROJECT > /tmp/gcp-SERVICE-logs-$(date +%Y%m%d-%H%M%S).json
Query Patterns
Logs by Service
# Single service
gcloud logging read \
'resource.labels.container_name="service-b"' \
--limit=500 \
--format=json \
--project=example-dev > /tmp/service-b-logs.json
# Multiple services (run separate queries)
gcloud logging read 'resource.labels.container_name="service-b"' --limit=500 --format=json > /tmp/service-b.json
gcloud logging read 'resource.labels.container_name="service-a"' --limit=500 --format=json > /tmp/service-a.json
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 · 206 lines · 46 tokens per session scan A 9b3a43b5ced5
gcp-locator is an agent published in the GitHub repository eveld/claude (10 stars, last pushed 7mo ago), licensed MIT. It adds 46 tokens to every session and 1,551 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 2026-08-31.
Other agents, from other repositories
coolify-architect
Coolify infrastructure architect.
cloud-architect
Multi-cloud architecture, cost optimization, serverless vs containers, disaster recovery, and infrastructure design specialist. Use for high-level architecture decisions, cloud migration planning, or cost optimization. Trigger phrases: cloud, AWS, GCP, Azure, serverless, containers, Kubernetes, infrastructure, cost…
ansible-security
Ansible Vault and secrets management specialist.
storage
Agent "storage" from WrongStack/WrongStack, covering working rules and output.
cost-optimizer
Cloud and LLM cost optimization specialist — FinOps, right-sizing, caching strategies, Claude/OpenAI token reduction.
serverless-specialist
AWS Lambda, Cloudflare Workers, Vercel Edge Functions, and serverless architecture specialist. Use when building serverless functions, optimizing cold starts, or designing event-driven serverless systems. Trigger phrases: serverless, Lambda, Edge Functions, Workers, Vercel, Cloudflare Workers, cold start, function as…