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 jpantsjoha/googlecloud-plugin --skill logging-monitoringgit clone --depth 1 https://github.com/jpantsjoha/googlecloud-pluginWrote 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/jpantsjoha/googlecloud-plugin/logging-monitoring)<a href="https://agentmods.dev/skills/jpantsjoha/googlecloud-plugin/logging-monitoring"><img src="https://agentmods.dev/badge/skills/jpantsjoha/googlecloud-plugin/logging-monitoring/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/jpantsjoha/googlecloud-plugin/logging-monitoring"><img src="https://agentmods.dev/badge/skills/jpantsjoha/googlecloud-plugin/logging-monitoring.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 | $0.00109 | $0.00930 |
| Opus 5 | $0.00055 | $0.00465 |
| Sonnet 5 | $0.00022 | $0.00186 |
| Haiku 4.5 | $0.00011 | $0.00093 |
Grade A, and why
logging-monitoring 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Logging + Monitoring
Full observability stack for GCP workloads: Cloud Logging, Cloud Monitoring, Cloud Trace, and Cloud Profiler.
Core Patterns
Create a log sink (export to BigQuery for long-term retention)
gcloud logging sinks create SINK_NAME \
bigquery.googleapis.com/projects/PROJECT_ID/datasets/DATASET \
--log-filter='resource.type="cloud_run_revision"' \
--project=PROJECT_ID
Create a log-based metric (count errors)
gcloud logging metrics create error-rate \
--description="Count of ERROR log entries" \
--log-filter='severity=ERROR' \
--project=PROJECT_ID
Create an alerting policy (notify on error spike)
# Best done via Terraform or Console for complex conditions
# CLI example for uptime check failure:
gcloud alpha monitoring policies create \
--policy-from-file=alerting-policy.json \
--project=PROJECT_ID
Uptime check
gcloud monitoring uptime create \
--display-name="Service Health Check" \
--resource-type=uptime-url \
--hostname=SERVICE_URL \
--path=/ \
--project=PROJECT_ID
Golden Signal Queries (Cloud Logging)
# 5xx errors on Cloud Run
resource.type="cloud_run_revision"
severity=ERROR
# Latency > 2s (requires structured logging with latency field)
resource.type="cloud_run_revision"
httpRequest.latency>"2s"
# GKE OOMKilled events
resource.type="k8s_container"
jsonPayload.reason="OOMKilling"
Safety Rules
- Log sinks can incur cost. Exporting logs to BigQuery, Cloud Storage, or Pub/Sub bills for storage and, in BigQuery's case, for queries over the exported data. Scope every sink with a tight
--log-filter— never exportseverity>=DEFAULT(i.e. everything) to a billable destination without intent. - Scope log filters narrowly. Broad filters (no
resource.type, noseverity) match high-volume logs and drive both ingestion and export cost. Always pinresource.typeand the minimumseverityyou need. - Exclusion filters reduce ingestion cost. Use log exclusions to drop high-volume, low-value logs (e.g. health-check 200s) before they are ingested and billed.
- Never log secrets. Application logs routed to Cloud Logging are readable by anyone with
roles/logging.viewer. Redact tokens, keys, and PII at the source; do not rely on downstream filtering. - Retention has a cost curve. Default retention is free to a point; extended retention on
_Default/custom buckets bills per GB. Set retention deliberately per bucket.
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.
- 10d ago First seen · 88 lines · 109 tokens per session scan A f8c536f0dfcc
logging-monitoring is a skill published in the GitHub repository jpantsjoha/googlecloud-plugin (4 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 930 once invoked, about $0.0005 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
ak-cloud-deploy
Deploy an Agent Kernel project to AWS, Azure, or GCP using Terraform modules, or to any Kubernetes cluster (on-prem, baremetal, EKS) using the official Helm chart. Supports serverless and containerized modes for all three clouds. AWS supports execution modes (restsync, restasync, async, stream), queue-based scalable…
vercel-deploy
Deploy an approved and tested committed web project to a Vercel preview and verify provider identity, commit, status and actual URL. Use for publishing a website preview; production needs separate approval, and feature building or browser QA belong to other skills.
qzcli
A command-line tool for managing GPU compute jobs on the Qizhi platform. GPU compute jobs use graphics processors to run demanding workloads such as machine-learning training.
serving-llms-vllm
Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
vast-gpu
Rent, manage, and destroy GPU instances on vast.ai. Use when user says "rent gpu", "vast.ai", "rent a server", "cloud gpu", or needs on-demand GPU without owning hardware.