jpantsjoha/googlecloud-plugin
A full Google Cloud delivery team for your coding agent — vendor-objective solution designer, GCP + agentic architects, security, SRE, and QA — wired into a design-first, security-first delivery gate. Installable on Claude Code, Antigravity
field: Data & analyticsCloud & infrastructure workflow: Frontend & designCI/CD & deployPlanning & specsSecurity reviewPR / code review
stack: Python
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
up to ~7.4k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Heavy · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add gcloud -e CLOUDSDK_CORE_PROJECT=YOUR_CLOUDSDK_CORE_PROJECT -- npx -y @google-cloud/gcloud-mcp $ claude mcp add toolbox -e GCP_PROJECT_ID=YOUR_GCP_PROJECT_ID -e GOOGLE_APPLICATION_CREDENTIALS=YOUR_GOOGLE_APPLICATION_CREDENTIALS -e TOOLBOX_TOOLS_FILE=YOUR_TOOLBOX_TOOLS_FILE -- npx -y @toolbox-sdk/server --stdio --config ${TOOLBOX_TOOLS_FILE} $ npx degit jpantsjoha/googlecloud-plugin/.claude ./rig-googlecloud-plugin # inspect, then merge into .claude/
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add gcloud -e CLOUDSDK_CORE_PROJECT=YOUR_CLOUDSDK_CORE_PROJECT -- npx -y @google-cloud/gcloud-mcp $ claude mcp add toolbox -e GCP_PROJECT_ID=YOUR_GCP_PROJECT_ID -e GOOGLE_APPLICATION_CREDENTIALS=YOUR_GOOGLE_APPLICATION_CREDENTIALS -e TOOLBOX_TOOLS_FILE=YOUR_TOOLBOX_TOOLS_FILE -- npx -y @toolbox-sdk/server --stdio --config ${TOOLBOX_TOOLS_FILE}
$ npx degit jpantsjoha/googlecloud-plugin/skills/agent-architect .claude/skills/agent-architect $ npx degit jpantsjoha/googlecloud-plugin/skills/bigquery .claude/skills/bigquery $ npx degit jpantsjoha/googlecloud-plugin/skills/cloud-run .claude/skills/cloud-run $ npx degit jpantsjoha/googlecloud-plugin/skills/cloud-storage .claude/skills/cloud-storage $ npx degit jpantsjoha/googlecloud-plugin/skills/gcp-architect .claude/skills/gcp-architect $ npx degit jpantsjoha/googlecloud-plugin/skills/gcp-ops .claude/skills/gcp-ops $ npx degit jpantsjoha/googlecloud-plugin/skills/gcp-qa .claude/skills/gcp-qa $ npx degit jpantsjoha/googlecloud-plugin/skills/gcp-security .claude/skills/gcp-security $ npx degit jpantsjoha/googlecloud-plugin/skills/gke .claude/skills/gke $ npx degit jpantsjoha/googlecloud-plugin/skills/iam .claude/skills/iam $ npx degit jpantsjoha/googlecloud-plugin/skills/logging-monitoring .claude/skills/logging-monitoring $ npx degit jpantsjoha/googlecloud-plugin/skills/mcp-servers .claude/skills/mcp-servers $ npx degit jpantsjoha/googlecloud-plugin/skills/networking .claude/skills/networking $ npx degit jpantsjoha/googlecloud-plugin/skills/solution-designer .claude/skills/solution-designer $ npx degit jpantsjoha/googlecloud-plugin/skills/terraform-gcp .claude/skills/terraform-gcp $ npx degit jpantsjoha/googlecloud-plugin/skills/vertex-ai .claude/skills/vertex-ai $ npx degit jpantsjoha/googlecloud-plugin/skills/well-architected .claude/skills/well-architected
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} MCP servers (2)
| server | source | est. tokens |
|---|---|---|
| @google-cloud/gcloud-mcp · "gcloud" env: CLOUDSDK_CORE_PROJECT | npm | 2.5k |
| @toolbox-sdk/server · "toolbox" env: GCP_PROJECT_ID, GOOGLE_APPLICATION_CREDENTIALS, TOOLBOX_TOOLS_FILE | npm | 2.5k |
Skills (17)
Similar rigs
wraith-proxy/wraith-skills
Agents don't hesitate before prod. wraith is the ghost that does. Skills and agents for data and infrastructure engineering on GCP: dbt, BigQuery, Cloud Run, Terraform, ODCS data contracts and ontologies.
Skill Collector 2.4k tok · · Q0
lordjabez/claude-code-config
Configuration items for Claude Code
YOLO Cowboy 44.2k tok · · Q0
aranculleton/last-job-search
An AI agent system on Claude Code that runs your whole job search: finds and scores roles, creates and tailors your resume for every role, finds who to message on LinkedIn, and reminds you to follow up.
Pragmatist 4.5k tok · · Q18
jacobzipper/vibian
The AI-native Linux distro: Ubuntu 26.04 LTS that boots to a terminal, and your coding agent (Claude Code, Codex, Gemini CLI, opencode, OpenClaw, pi, Cursor) builds the desktop. btrfs snapshots, a change ledger and undo for everything.
Skill Collector 2.6k tok · · Q0