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 GoogleCloudPlatform/gemini-cloud-assist-mcp --skill preferencesgit clone --depth 1 https://github.com/GoogleCloudPlatform/gemini-cloud-assist-mcpWrote 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/googlecloudplatform/gemini-cloud-assist-mcp/preferences)<a href="https://agentmods.dev/skills/googlecloudplatform/gemini-cloud-assist-mcp/preferences"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/gemini-cloud-assist-mcp/preferences/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/googlecloudplatform/gemini-cloud-assist-mcp/preferences"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/gemini-cloud-assist-mcp/preferences.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 | $0.00084 | $0.00591 |
| Opus 5.5 | $0.00034 | $0.00236 |
| Sonnet 5.5 | $0.00017 | $0.00118 |
| Haiku 4.5 | $0.00008 | $0.00059 |
Grade A, and why
preferences 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remember GCP operating preferences
Preferences live in a Markdown file outside the plugin,
~/.config/cloud-operator/preferences.md, which the other Cloud Operator client plugins
share. The operator skill reads it and sends it with the first
ask_cloud_operator call of every Operator session. Keep it short,
declarative and free of secrets.
Read the existing file first (create it and its folder if missing) and merge into it: replace bullets the new answers contradict, don't add duplicates, and keep every section the user doesn't change, including ones not listed below.
/cloud-operator:preferences <preference>
Rewrite it as one imperative bullet (e.g. "Never touch prod; apply to dev only after explicit approval.") under the matching section below, replacing any bullet it contradicts. Show the user the stored bullet.
/cloud-operator:preferences alone: interview
Ask in one message, pre-filling from the existing file and anything GCP-related you already know from GEMINI.md / AGENTS.md, memories or this conversation. The user may skip any.
- Projects & environments - dev/staging/prod projects or naming pattern (the default project comes from gcloud config, not from here).
- Regions - primary and DR regions; forbidden regions.
- IaC & tooling - Terraform / Pulumi / Config Connector / gcloud; versions, modules, state backend.
- Naming & labels - naming pattern; required labels.
- Security & compliance - CMEK, VPC-SC, service accounts, public IPs, frameworks (PCI, HIPAA, SOC 2).
- Change policy - extra limits on changes (e.g. "never touch prod", "no IAM changes without a ticket").
- Cost guardrails - budgets, Spot, committed use.
- Output style - diagrams, verbosity.
Write the answers as ### sections with these names, in this order, one
imperative bullet per preference, omitting empty sections.
Then tell the user
- Where the file is, and that the preferences go to the Operator Agent at the start of every new Operator session from now on.
/cloud-operator:preferences <text>updates one item; they can also edit or delete the file directly.
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 · 52 lines · 84 tokens per session scan A c831658a9c26
preferences is a skill published in the GitHub repository GoogleCloudPlatform/gemini-cloud-assist-mcp (69 stars, last pushed 2d ago), licensed Apache-2.0. It adds 84 tokens to every session and 591 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-18.
Other skills, from other repositories
cloud-run
Manage Cloud Run services and jobs.
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
n8n-self-hosting
Deploy a production self-hosted n8n end-to-end to a fresh Linux VM over SSH, using Docker Compose behind a Caddy reverse proxy with automatic HTTPS. Use whenever the user wants to self-host, install, set up, provision, or deploy n8n on their own server/VPS/box (Hetzner, DigitalOcean, AWS EC2, bare metal, etc.) — in…
kubernetes
Deploy, manage, and debug Kubernetes in production — Deployments, Services, Gateway API, Service Mesh (Istio/Linkerd/Cilium), eBPF observability (Cilium Hubble), security hardening (Pod Security Standards, OPA/Kyverno, seccomp, runtime security with Falco/Tetragon), Helm, HPA, PDB, topology spread, and debugging. Use…
zdx-investigate-multi-app-outage
Diagnose a multi-application outage scoped to one location by correlating ZDX alerts, affected devices, and shared cloud-path hops. Identifies the devices affected at a specific office, compares the per-application network path across multiple SaaS apps to surface the common network bottleneck, and produces an…
gcp-expert
Expert-level Google Cloud Platform, services, and cloud architecture. Use when the user mentions Google Cloud, Cloud Functions, BigQuery, or Firestore.