agents-cli is a command-line tool and collection of skills that guides coding assistants through building, evaluating, and deploying AI agents on Google's Gemini Enterprise Agent Platform. Developers use it with assistants such as Claude Code, Codex, and Antigravity CLI to work with Google Cloud agent services. The catalogue entries provide skills and a plugin for that development workflow.
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 google/agents-cli --skill google-agents-cli-deploygit clone --depth 1 https://github.com/google/agents-cliWrote 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/google/agents-cli/google-agents-cli-deploy)<a href="https://agentmods.dev/skills/google/agents-cli/google-agents-cli-deploy"><img src="https://agentmods.dev/badge/skills/google/agents-cli/google-agents-cli-deploy/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/google/agents-cli/google-agents-cli-deploy"><img src="https://agentmods.dev/badge/skills/google/agents-cli/google-agents-cli-deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 130 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 136 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Privilege Escalation · line 256 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 130 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 136 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00153 | $0.07140 |
| Opus 5.5 | $0.00061 | $0.02856 |
| Sonnet 5.5 | $0.00031 | $0.01428 |
| Haiku 4.5 | $0.00015 | $0.00714 |
Grade A, and why
google-agents-cli-deploy scanned grade A 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **`testing-deployed-agents.md`** — Testing instructions per deployment target, curl examples, load tests Copies of this mod
1 near-identical copy found in the catalogue:
- google-agents-cli-deploy — 91% identical, 56 lines differ
How it starts
The opening of the file, as written. The whole thing — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deployment Guide
Requires:
agents-cli(uv tool install google-agents-cli) — install uv first if needed.
Prefer using the
agents-clicommands throughout this guide — they wrap Terraform, Docker, and deployment into a tested pipeline. If your project isn't scaffolded yet, see/google-agents-cli-scaffoldto add deployment support first.
Reference Files
For deeper details, consult these reference files in references/:
cloud-run.md— Scaling defaults, Dockerfile, session types, networkingagent-runtime.md— container-based deploy, unified FastAPI app, the/apipassthrough, Terraform resource, deployment metadata, CI/CD differencesgke.md— GKE Autopilot cluster, Kubernetes manifests, Workload Identity, session types, networkingterraform-patterns.md— Custom infrastructure, IAM, state management, importing resourcesbatch-inference.md— BigQuery Remote Function trigger; for Pub/Sub / Eventarc on ADK see/google-agents-cli-adk-codecicd-pipeline.md— Full CI/CD pipeline setup,infra cicdflags, runner comparison, WIF auth, pipeline stagestesting-deployed-agents.md— Testing instructions per deployment target, curl examples, load testscmek.md— Customer-managed encryption keys on Agent Runtime in Gemini platform: key grants,deploy --keyfor dev, Terraform edits for staging/prod
Observability: See the
/google-agents-cli-observabilityskill for Cloud Trace, prompt-response logging, BigQuery Analytics, and third-party integrations.
Deployment Target Decision Matrix
Choose the right deployment target based on your requirements:
| Criteria | Agent Runtime | Cloud Run | GKE |
|---|---|---|---|
| Scaling | Managed auto-scaling (configurable min/max, concurrency) | Fully configurable (min/max instances, concurrency, CPU allocation) | Full Kubernetes scaling (HPA, VPA, node auto-provisioning) |
| Networking | VPC-SC and PSC-I supported (private VPC connectivity via network attachments) | Full VPC support, direct VPC egress, IAP, ingress rules | Full Kubernetes networking |
| Session state | Sessions in Gemini platform (ADK wires VertexAiSessionService automatically) |
In-memory (dev), Cloud SQL, or a managed sessions backend | In-memory (dev), Cloud SQL, or a managed sessions backend |
| Batch/event processing | Trigger endpoints reachable via the Agent Runtime /api passthrough |
Native trigger endpoints (Pub/Sub, Eventarc); ADK: see /google-agents-cli-adk-code |
Custom (Kubernetes Jobs, Pub/Sub) |
| Cost model | vCPU-hours + memory-hours (not billed when idle) | Per-instance-second + min instance costs | Node pool costs (always-on or auto-provisioned) |
| Setup complexity | Lower (managed, purpose-built for agents) | Medium (Dockerfile, Terraform, networking) | Higher (Kubernetes expertise required) |
| Best for | Managed infrastructure, minimal ops | Custom infra, full networking control | Full Kubernetes control |
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed · +2 lines 12a4df554a53
- 9d ago Changed · +9 lines 68552fd389d8
- 15d ago Changed acce197d82dc
- 23d ago Changed · +4 lines a2951408cc0a
- 29d ago Changed 84b195959dca
- 1mo ago Changed · +2 lines · +15 tokens per session 58f5ca47c93e
- 1mo ago First seen · 427 lines · 138 tokens per session scan A 830e3d2b4e53
google-agents-cli-deploy is a skill published in the GitHub repository google/agents-cli (6,094 stars, last pushed 4d ago), licensed Apache-2.0. It adds 153 tokens to every session and 7,140 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
finops-expert
Expert-level cloud financial operations, cost optimization, and cloud economics. Use when the user mentions cloud cost, optimization, cloud economics, or AWS cost, or when the task involves FinOps Fundamentals, Cost Management, FinOps Practices, or Cost Visibility.
cloudflare-expert
Expert-level Cloudflare Workers, CDN, edge computing, and security services. Use when the user mentions edge computing, CDN, workers, or WAF, or when the task involves Cloudflare Services or Developer Tools.
aws-expert
Expert-level AWS cloud architecture, services, security, cost optimization, and best practices. Use when the user mentions cloud, infrastructure, devops, or serverless, or when the task involves Compute Services, Storage Services, Database Services, or Networking.
azure-expert
Expert-level Microsoft Azure cloud platform, services, and architecture. Use when the user mentions cloud, Microsoft platforms, Azure Functions, or Cosmos DB.
gcp-expert
Expert-level Google Cloud Platform, services, and cloud architecture. Use when the user mentions Google Cloud, Cloud Functions, BigQuery, or Firestore.
databricks-expert
Expert-level Databricks platform, Apache Spark, Delta Lake, MLflow, notebooks, and cluster management. Use when the user mentions Apache Spark, Delta Lake, MLflow, lakehouse architecture, or PySpark, or when the task involves Cluster Configuration and Management, Delta Lake Architecture, PySpark Data Processing, or…