Agents CLI: Deployment
Part of Google's agents-cli skills suite. Walks through the deployment-target decision matrix (Agent Runtime vs Cloud Run vs GKE — scaling, networking, session state, batch/event processing, cost model, and setup complexity for each), then covers service accounts, CI/CD pipeline setup, secrets configuration, rollback, and production infrastructure via `agents-cli deploy` and `agents-cli infra`. Applies to any framework agents-cli can deploy (ADK, LangChain, and others via the extension system), not just ADK. Does not cover ADK API code patterns (google-agents-cli-adk-code), evaluation (google-agents-cli-eval), or project scaffolding (google-agents-cli-scaffold).
This skill hasn't been reviewed yet.
What it does
Deployment guidance for agents built with Google's agents-cli — choosing between Agent Runtime, Cloud Run, and GKE, plus CI/CD, secrets, and rollback.
How to use this
Once it is installed, this skill picks itself up. You do not need to name it.
- Created by
- Google LLC
- Category
- Engineering
- Source
- View source
Run this on Skills and Agents
You can run the skill on Skills and Agents by creating an account. You don't need to install anything. We provide the model and tokens. Your connected tools and company brain are ready to use.
Skills give you best practices and templates to get the most out of your AI
Add this skill
Pick where you want it. Nothing to configure after.
These install links go live once the signup flow ships. Until then, ask Claude, ChatGPT, or Gemini to fetch this skill's file directly from GitHub.
Not sure which? See the install guide.
Share this skill
Agents CLI: Deployment
Part of Google's agents-cli skills suite. Walks through the deployment-target decision matrix (Agent Runtime vs Cloud Run vs GKE — scaling, networking, session state, batch/event processing, cost model, and setup complexity for each), then covers service accounts, CI/CD pipeline setup, secrets configuration, rollback, and production infrastructure via `agents-cli deploy` and `agents-cli infra`. Applies to any framework agents-cli can deploy (ADK, LangChain, and others via the extension system), not just ADK. Does not cover ADK API code patterns (google-agents-cli-adk-code), evaluation (google-agents-cli-eval), or project scaffolding (google-agents-cli-scaffold).
Third-party, by Google LLC
September 13, 2026
Install from google/agents-cli
This skill is one of 7 bundled in Google's agents-cli repo (skills/google-agents-cli-deploy). Installing pulls all 7 skills in the repo — there's no way to grab just this one.
- 1
Install all 7 agents-cli skills
Installs this skill along with the other 6 (workflow, adk-code, scaffold, eval, publish, observability) from google/agents-cli's skills/ folder.
npx skills add google/agents-cli - 2
Install the CLI itself (required to actually deploy)
agents-cli deploy wraps Terraform, Docker, and the deployment pipeline — the skill is guidance for using it, not a replacement for it.
uv tool install google-agents-cli - 3
Activate in Claude
Ask to deploy an agent, set up CI/CD, configure secrets, or troubleshoot a failed deployment.
Your skill is downloading.
Create a free account and the platform does the rest:
- Get an email the moment this skill updates
- See every skill and agent you've installed, in one place
- Get your next recommendation based on what you actually use
No credit card. Takes about a minute.
What this skill does
This is an overview of the skill from the site, not the skill's real instructions. The full SKILL.md Claude reads when this skill is active lives on GitHub at the source below.
A skill from Google’s
google/agents-cli. The canonical source — including the CLI, the other 6 skills, and release notes — lives in that repo.
What this skill does
Guides agents-cli deploy and agents-cli infra, which wrap Terraform, Docker, and the deployment pipeline into a tested workflow, across three deployment targets.
Deployment target decision matrix
| Criteria | Agent Runtime | Cloud Run | GKE |
|---|---|---|---|
| Scaling | Managed auto-scaling | Fully configurable | Full Kubernetes scaling (HPA/VPA) |
| Session state | Managed Agent Engine sessions | In-memory, Cloud SQL, or Agent Platform Sessions | Same as Cloud Run |
| Setup complexity | Lower (managed, purpose-built) | Medium (Dockerfile, Terraform, networking) | Higher (Kubernetes expertise) |
| Best for | Managed infra, minimal ops | Custom infra, full networking control | Full Kubernetes control |
All three are container-based, so any language works. The skill flags two decision points worth calling out directly:
- Ambient / scheduled / event-driven agents register the same trigger endpoints on all three targets, but they’re reached differently — public HTTP routes on Cloud Run/GKE (point a Pub/Sub push subscription or Eventarc trigger at them) versus through the Agent Runtime
/apipassthrough. - OAuth / user-consent agents (e.g. accessing a user’s Drive or Calendar) need Agent Runtime with Gemini Enterprise — Cloud Run does not currently support managed OAuth flows.
Reference files it points to
Per-target guides for Cloud Run, Agent Runtime, and GKE; Terraform patterns for custom infrastructure and IAM; batch inference via BigQuery Remote Functions; a full CI/CD pipeline guide (runner comparison, Workload Identity Federation auth, pipeline stages); and testing instructions per target.
Scope
Framework-agnostic. Does not cover ADK API code patterns (google-agents-cli-adk-code), evaluation (google-agents-cli-eval), or project scaffolding (google-agents-cli-scaffold). Observability setup (Cloud Trace, logging, BigQuery Analytics) is covered separately in google-agents-cli-observability.