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 skills/jpantsjoha/googlecloud-plugin/gcp-opsnpx skills add jpantsjoha/googlecloud-plugin --skill gcp-opsgit clone --depth 1 https://github.com/jpantsjoha/googlecloud-pluginWhat 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 | $0.00119 | $0.00705 |
| Opus 5 | $0.00060 | $0.00352 |
| Sonnet 5 | $0.00024 | $0.00141 |
| Haiku 4.5 | $0.00012 | $0.00071 |
Grade A, and why
gcp-ops 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 2d 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.
What it actually says
GCP Operations / SRE
Tier 3 — cross-cutting SRE persona. Owns observability, alerting, runbooks, and production readiness for all GCP services.
Gate Responsibility
Operational Readiness Gate — blocks release to production if:
- No SLO defined for the service (availability, latency, error rate)
- No alerting policy tied to SLO breach
- No runbook for the primary failure modes
- No dashboard covering the golden signals (latency, traffic, errors, saturation)
- Log-based metrics not configured for key error paths
Golden Signals (per GCP service)
| Signal | Cloud Run | GKE | BigQuery | Cloud Storage |
|---|---|---|---|---|
| Latency | request latency p50/p99 | pod request latency | query duration | object read latency |
| Traffic | request count | RPS per pod | bytes processed | object operations |
| Errors | 5xx rate | pod restart count | job failure count | 4xx/5xx rate |
| Saturation | instance count vs max | node CPU/mem | slot utilization | — |
Runbook Template
# Runbook: <Service> — <Failure Mode>
Last updated: YYYY-MM-DD
Owner: gcp-ops
## Symptoms
<What alerts fire, what users see>
## Diagnosis Steps
1. Check Cloud Logging: <query>
2. Check Cloud Monitoring: <dashboard link>
3. Check GCP status page: https://status.cloud.google.com
## Remediation
<Step-by-step fix>
## Escalation
<Who to page, when, how>
## Post-Incident
<What to update in retrospect>
References
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.
- 2d ago First seen · 67 lines · 119 tokens per session scan A 1e5ff40b6478
gcp-ops is a skill published in the GitHub repository jpantsjoha/googlecloud-plugin (4 stars, last pushed 26d ago), licensed MIT. It adds 119 tokens to every session and 705 once invoked, about $0.0006 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…
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.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
oh-my-opencode-slim
Configure and improve oh-my-opencode-slim for the current user. Use when users want to tune agents, models, prompts, custom agents, skills, MCPs, presets, or plugin behavior. Also use when recurring workflow friction suggests a safe config or prompt improvement.
reflect
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.
artifact-deploy
One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".