Project Scaffolding Guide
Requires: agents-cli (uv tool install google-agents-cli) — install uv first if needed.
Use the agents-cli CLI to create new agent projects or enhance existing ones with deployment, CI/CD, and infrastructure scaffolding.
Prerequisite: Clarify Requirements (MANDATORY for new projects)
Before scaffolding a new project, load /google-agents-cli-workflow and complete Phase 0 — clarify the user's requirements before running any scaffold create command. Ask what the agent should do, what tools/APIs it needs, and whether they want a prototype or full deployment.
Step 1: Choose Architecture
Mapping user choices to CLI flags:
| Choice |
CLI flag |
| Retrieval/RAG, sandboxed execution, cross-session memory, OAuth consent, guardrails, scheduled runs |
No flag — these come from clone-and-study recipes. ADK: see the topic index in /google-agents-cli-adk-code → references/samples.md; on other frameworks, see the sample index the framework template ships |
| A2A protocol |
built into the scaffolded app — scaffold normally (ADK: --agent adk, the default) |
| Prototype (no deployment) |
--prototype |
| Deployment target |
`--deployment-target <agent_runtime\ |
cloud_run\ |
gke>` |
| CI/CD runner |
`--cicd-runner <github_actions\ |
googlecloudbuild>` |
| Session storage |
`--session-type <in_memory\ |
cloud_sql\ |
agentplatformsessions>` |
Product name mapping
Older names → CLI values (vertexai SDK package name unchanged):
- Agent Engine / Vertex AI Agent Engine →
--deployment-target agent_runtime
- Agent Engine sessions / Agent Platform Sessions →
--session-type agentplatformsessions
- Vertex AI Search / Vertex AI Vector Search / RAG → clone-and-study recipe, not a flag
Removed flags. --datastore, the agentic_rag template, and agents-cli infra datastore /
agents-cli data-ingestion no longer exist. If you reach for one, you want a recipe instead.
Step 2: Create or Enhance the Project
Create a New Project
agents-cli scaffold create <project-name> \
--agent <template> \
--deployment-target <target> \
--region <region> \
--prototype
Constraints:
- Project name must be 26 characters or less, lowercase letters, numbers, and hyphens only.
- Do NOT
mkdir the project directory before running create — the CLI creates it automatically. If you mkdir first, create will fail or behave unexpectedly.
- Auto-detect the guidance filename based on the IDE you are running in and pass
--agent-guidance-filename accordingly (GEMINI.md for Antigravity CLI, CLAUDE.md for Claude Code, AGENTS.md for OpenAI Codex/other).
- When enhancing an existing project, check where the agent code lives. If it's not in
app/, pass --agent-directory <dir> (e.g. --agent-directory agent). Getting this wrong causes enhance to miss or misplace files.
Reference Files
| File |
Contents |
references/flags.md |
Full flag reference for create and enhance commands |
Enhance an Existing Project
agents-cli scaffold enhance . --deployment-target <target>
agents-cli scaffold enhance . --cicd-runner <runner>
Run this from inside the project directory (or pass the path instead of .).
Upgrade a Project
Upgrade an existing project to a newer agents-cli version, intelligently applying updates while preserving your customizations:
agents-cli scaffold upgrade # Upgrade current directory
agents-cli scaffold upgrade <project-path> # Upgrade specific project
agents-cli scaffold upgrade --dry-run # Preview changes without applying
agents-cli scaffold upgrade --auto-approve # Auto-apply non-conflicting changes
Execution Modes
The CLI defaults to strict programmatic mode — all required params must be supplied as CLI flags or a UsageError is raised. No approval flags needed. Pass all required params explicitly.
Common Workflows
Always ask the user before running these commands. Present the options (CI/CD runner, deployment target, etc.) and confirm before executing.
# Add deployment to an existing prototype (strict programmatic)
agents-cli scaffold enhance . --deployment-target agent_runtime
# Add CI/CD pipeline (ask: GitHub Actions or Cloud Build?)
agents-cli scaffold enhance . --cicd-runner github_actions
Template Options
| Template |
Deployment |
Description |
adk |
Agent Runtime, Cloud Run, GKE |
Standard ADK agent (default); A2A protocol built in |
adk is the only built-in template. Other frameworks ship as template repos you scaffold
from directly: --agent google/agents-cli/extensions/langchain/[email protected], with nothing installed. The first-party LangChain
template is extensions/langchain/template/ in the agents-cli repo; see
/google-agents-cli-workflow → references/extension.md to publish your own. Capabilities
beyond the template — retrieval, sandboxed execution, memory, OAuth, guardrails — are
clone-and-study recipes, not templates. ADK: see the topic index in
/google-agents-cli-adk-code → references/samples.md.
Deployment Options
| Target |
Description |
agent_runtime |
Managed by Google (Vertex AI Agent Runtime). Container-based — Agent Engine builds the project Dockerfile. Sessions handled automatically. |
cloud_run |
Container-based deployment. More control; you build and deploy the Dockerfile. |
gke |
Container-based on GKE Autopilot. Full Kubernetes control. |
none |
No deployment scaffolding. Code only (still includes a Dockerfile). |
"Prototype First" Pattern (Recommended)
Start with --prototype to skip CI/CD and Terraform. Focus on getting the agent working first, then add deployment later with scaffold enhance:
# Step 1: Create a prototype
agents-cli scaffold create my-agent --agent adk --prototype
# Step 2: Iterate on the agent code...
# Step 3: Add deployment when ready
agents-cli scaffold enhance . --deployment-target agent_runtime
Agent Runtime and session_type
When using agentruntime as the deployment target, Agent Runtime manages sessions internally. If your code sets a sessiontype, clear it — Agent Runtime overrides it.
Step 3: Load Dev Workflow
After scaffolding, immediately load /google-agents-cli-workflow — it contains the development workflow, coding guidelines, and operational rules you must follow when implementing the agent.
Key files to customize: app/agent.py (instruction, tools, model), app/tools.py (custom tool functions), .env (project ID, location, API keys). Files to preserve: agents-cli-manifest.yaml (CLI reads this), deployment configs under deployment/, Makefile, and the generated runtime/A2A infra (app/fastapiapp.py, Dockerfile, and whatever your template puts under app/apputils/) — these wire up serving, sessions, and the built-in A2A surface; don't hand-edit them. ADK: app/init.py (the App(name=...) must match the directory name — default app), app/apputils/a2a.py, app/app_utils/services.py.
Adapting a recipe: copy its app/, infra/terraform/, and any ingestion or provisioning into your scaffolded project, then run provisioning from the recipe's own Makefile (e.g. make setup-infra). Start from its AGENTS.md.
Verifying your agent works: Use agents-cli run "test prompt" for quick smoke tests, then agents-cli eval run for systematic validation. Do NOT write pytest tests that assert on LLM response content, that belongs in eval.
Scaffold as Reference
When you need specific files (Terraform, CI/CD workflows, Dockerfile) but don't want to scaffold the current project directly, create a temporary reference project in /tmp/:
agents-cli scaffold create ref-project --output-dir /tmp \
--agent adk \
--deployment-target cloud_run
Inspect the generated files, adapt what you need, and copy into the actual project. Delete the reference project when done.
This is useful for:
- Non-standard project structures that
enhance can't handle
- Cherry-picking specific infrastructure files
- Understanding what the CLI generates before committing to it
Critical Rules
- NEVER skip requirements clarification — load
/google-agents-cli-workflow Phase 0 and clarify the user's intent before running scaffold create
- NEVER change the model in existing code unless explicitly asked
- NEVER
mkdir before create — the CLI creates the directory; pre-creating it causes enhance mode instead of create mode
- NEVER create a Git repo or push to remote without asking — confirm repo name, public vs private, and whether the user wants it created at all
- Always ask before choosing CI/CD runner — present GitHub Actions and Cloud Build as options, don't default silently
- Agent Runtime clears sessiontype — if deploying to
agentruntime, remove any session_type setting from your code
- Start with
--prototype for quick iteration — add deployment later with enhance
- Project names must be ≤26 characters, lowercase, letters/numbers/hyphens only
- NEVER write A2A code from scratch — A2A is built into the scaffolded app (the
adk template and framework templates alike); the A2A Python API surface (import paths, AgentCard schema, to_a2a() signature) is non-trivial and changes across versions. Scaffold normally; never hand-write the A2A surface.
Examples
Using scaffold as reference: User says: "I need a Dockerfile for my non-standard project" Actions:
- Create temp project:
agents-cli scaffold create ref --output-dir /tmp --agent adk --deployment-target cloud_run
- Copy relevant files (Dockerfile, etc.) from /tmp/ref
- Delete temp project
Result: Infrastructure files adapted to the actual project
A2A project: User says: "Build me a Python agent that exposes A2A and deploys to Cloud Run" Actions:
- Follow the standard flow (understand requirements, choose architecture, scaffold)
agents-cli scaffold create my-a2a-agent --agent adk --deployment-target cloud_run --prototype
Result: Valid A2A imports and Dockerfile — no manual A2A code written.
Troubleshooting
agents-cli command not found
See /google-agents-cli-workflow → Setup section.
Related Skills
/google-agents-cli-workflow — Development workflow, coding guidelines, and the build-evaluate-deploy lifecycle
/google-agents-cli-adk-code — ADK Python API quick reference for writing agent code (ADK projects)
/google-agents-cli-deploy — Deployment targets, CI/CD pipelines, and production workflows
/google-agents-cli-eval — Evaluation methodology, dataset schema, and the eval-fix loop