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 setupgit 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/setup)<a href="https://agentmods.dev/skills/googlecloudplatform/gemini-cloud-assist-mcp/setup"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/gemini-cloud-assist-mcp/setup/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/setup"><img src="https://agentmods.dev/badge/skills/googlecloudplatform/gemini-cloud-assist-mcp/setup.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 | $0.00072 | $0.01347 |
| Opus 5.5 | $0.00029 | $0.00539 |
| Sonnet 5.5 | $0.00014 | $0.00269 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade C, and why
setup scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
ADC="${GOOGLE_APPLICATION_CREDENTIALS:-${CLOUDSDK_CONFIG:-$HOME/.config/gcloud}/application_default_credentials.json}" How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Operator plugin setup
Run the checks below, fix what you can, and end with a status table. Ask the
user only when a step needs them. None of the checks need the gcloud binary
(Antigravity reads ADC itself); when a fix needs gcloud, tell the user to run
it in their own terminal.
1. Default project
Read the active gcloud configuration's project from its config file:
CFG="${CLOUDSDK_CONFIG:-$HOME/.config/gcloud}"; echo "${CLOUDSDK_CORE_PROJECT:-$(sed -n 's/^project *= *//p' "$CFG/configurations/config_${CLOUDSDK_ACTIVE_CONFIG_NAME:-$(cat "$CFG/active_config" 2>/dev/null || echo default)}" 2>/dev/null)}"
If it's empty, the user runs gcloud config set project <project-id> (the
project their Operator agent lives in, or will live in); until then, ask them
which project to use.
2. ADC file and quota project
Read only the type and quota_project_id fields of the ADC file. Never
print the whole file: it contains a refresh token. If the command below
prints nothing, treat it as no quota project; don't open the file any other
way.
ADC="${GOOGLE_APPLICATION_CREDENTIALS:-${CLOUDSDK_CONFIG:-$HOME/.config/gcloud}/application_default_credentials.json}"
if [ -f "$ADC" ]; then grep -oE '"(type|quota_project_id)": *"[^"]*"' "$ADC"; else echo NO_ADC_FILE; fi
NO_ADC_FILE→ the user runsgcloud auth application-default login, then restarts Antigravity.- No
quota_project_id→ the user runsgcloud auth application-default set-quota-project <project-id>(needsserviceusage.services.useon that project), then restarts Antigravity.
3. Smoke test
Check that an MCP server whose name ends in autocloud is connected and lists
ask_cloud_operator. If not, turn the plugin on in /plugin (a new install
can start disabled), check ... > MCP Servers, and restart Antigravity.
Call ask_cloud_operator with project set to projects/<default project>
and userQuery set to Hello. In two sentences, confirm which project you are operating in and list the capabilities you offer. Expect a reply and a
context_id; the first call can take 1-3 minutes while a sandbox warms up.
Then call search_operator_sessions for the same project; the hello session
should be the newest by createTime.
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 · 105 lines · 72 tokens per session scan C b0cc486af16c
setup 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 72 tokens to every session and 1,347 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (reaches for credential files). 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.