google-agents-cli-observability Skill for Claude: Monitor Deployed ADK Agents
Teaches Claude to set up tracing, prompt-response logging and BigQuery analytics for agents deployed with agents-cli.
- Installs
- 532.1K
- on skills.sh
- Stars
- 6.3K
- on GitHub
- Files
- 4
- besides SKILL.md
- Updated
- Oct 2026
- last repo commit
google-agents-cli-observability covers four levels of monitoring for ADK agents. Cloud Trace is always on. Prompt-response logging, BigQuery Agent Analytics and third-party tools such as AgentOps, Phoenix and MLflow are the other three. It asks which levels you want and they can be combined.
The prompt-response logs need Terraform-provisioned infrastructure, from agents-cli infra single-project --apply. By default in a Terraform deploy, full prompts and responses go to Cloud Storage and BigQuery, but not into trace spans. Decide what you are willing to store before you apply.
Good for
- Developers debugging a deployed ADK agent
- Teams who must audit LLM interactions
- Anyone building dashboards on agent events
Install google-agents-cli-observability
Claude Code
- 1
Copy this prompt.
Install the google-agents-cli-observability skill in Claude Code. Run this command: uvx google-agents-cli setup Then check that it loaded and tell me how to use it.
- 2
Paste it into Claude Code. It shows the change and asks before running it.
Requires Python 3.11+, uv, Node.js.
Pick one route. setup installs the agents-cli program and the skills into your coding agent. The README says that with the skills-only route your coding agent handles the rest. The seven skills in the suite point to each other, so take the whole set.
From the project README. Source.
What's in the skill
When it loads
This skill should be used when the user wants to "set up tracing", "monitor my agent", "configure logging", "add observability", "debug production traffic", or needs guidance on monitoring deployed agents, including ADK (Agent Development Kit) agents. Covers Cloud Trace, prompt-response logging, BigQuery Agent Analytics, third-party integrations (AgentOps, Phoenix, MLflow, etc.), and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment setup (use google-agents-cli-deploy) or API code patterns (use google-agents-cli-adk-code).
Sections in SKILL.md
- Deployment order
- Reference Files
- Observability Tiers
- Cloud Trace
- Span Hierarchy
- Setup by Deployment Type
- Prompt-Response Logging
- BigQuery Agent Analytics Plugin
- Third-Party Integrations
- Troubleshooting
- Related Skills
Key facts
- Author
- Last commit
- Oct 27, 2026
- skills.sh audits
- Gen Agent Trust Hub pass, Socket pass, Snyk warn
What it includes
OpenTelemetry traces of agent runs, always enabled
Shows execution flow, latency and errors.
Network ·
Cloud TraceExports prompts and responses to Cloud Storage, BigQuery and Cloud Logging
Disabled locally, enabled when deployed with Terraform; full content by default.
Write ·
Prompt-response loggingLogs structured agent events to BigQuery
Opt-in with --bq-analytics at scaffold time.
Write ·
BigQuery Agent AnalyticsAgentOps, Phoenix, MLflow and more via OpenTelemetry
Network ·
Third-party integrationsRuns Terraform to provision logging resources
Needed before deploy if you want Terraform-managed observability.
Runs code ·
infra single-project --applyFixes missing traces and logs
Read ·
Troubleshooting
From the official docs
Permissions
Medium risk
Claude can run Terraform that creates cloud resources and stores full prompts and responses in your Google Cloud project. Decide what you may keep before you apply.
What it can do
- Read your data
- Create and change things
- Delete things
- Read-only mode
Watch out for
Full prompts and responses are stored by default
In a Terraform deploy, the logging tier keeps full content in Cloud Storage and BigQuery. Turn it off if your users' data should not be kept.
It creates cloud resources
infra single-project --apply provisions real infrastructure. Read the Terraform plan first.
skills.sh audit: Snyk warn
Gen Agent Trust Hub and Socket pass; Snyk is listed as warn. Read the audit on skills.sh before installing.
Technical details
| Scopes |
|
|---|
Questions
What does google-agents-cli-observability do?
It teaches Claude to set up monitoring for deployed ADK agents: Cloud Trace, prompt-response logging, BigQuery Agent Analytics and third-party tools.
How do I install it?
Use the install box at the top of this page. The setup command installs the agents-cli program and all seven skills in the suite, which is what you want. The README says that with the skills-only route your coding agent handles the rest. You need Python 3.11+, uv and Node.js first.
Does it store my users' prompts?
It can. In a Terraform deploy the SKILL.md says full prompts and responses go to Cloud Storage and BigQuery by default. Trace spans carry no content by default.
What works with no setup?
Cloud Trace works out of the box with no infrastructure. The logging and BigQuery tiers need Terraform-provisioned resources.
Does it need an API key?
The SKILL.md names no API key. It needs the agents-cli program and a Google Cloud sign-in, which agents-cli login handles; the README says login also supports AI Studio.
Is it safe?
It creates cloud resources and can store conversation content, so review the plan. skills.sh lists Gen Agent Trust Hub and Socket as pass and Snyk as warn.
Does it work in the Claude app, Codex or Cursor?
The README names Antigravity CLI, Claude Code and Codex, and says any other coding agent works too. It does not name the Claude desktop or web app or Cursor.
Information
updated Nov 2, 2026
- Repository
- google/agents-cli
- Folder
skills/google-agents-cli-observability
Sources
Docs, issue trackers and discussions this page is built from.
Show all 3Hide
- google/agents-cli README · github.com
- google-agents-cli-observability SKILL.md · github.com
- google-agents-cli-observability on skills.sh · skills.sh