Agents CLI: Observability
Part of Google's agents-cli skills suite. Covers four observability tiers for a deployed agent: Cloud Trace (distributed tracing via OpenTelemetry, always on, no infra needed), prompt-response logging (GenAI interactions exported to GCS/BigQuery/Cloud Logging, requires Terraform-provisioned infra), BigQuery Agent Analytics (structured agent events for ADK agents with the plugin enabled), and third-party integrations (AgentOps, Phoenix, MLflow, and others via OpenTelemetry). Also documents the specific ordering requirement for agent_runtime deployments — provisioning infra before the first deploy — and how to retrofit observability onto an agent that was already deployed via the SDK. Does not cover deployment setup (google-agents-cli-deploy) or ADK API code patterns (google-agents-cli-adk-code).
This skill hasn't been reviewed yet.
What it does
Monitoring guidance for agents deployed with Google's agents-cli — Cloud Trace, prompt-response logging, BigQuery Agent Analytics, and third-party integrations.
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: Observability
Part of Google's agents-cli skills suite. Covers four observability tiers for a deployed agent: Cloud Trace (distributed tracing via OpenTelemetry, always on, no infra needed), prompt-response logging (GenAI interactions exported to GCS/BigQuery/Cloud Logging, requires Terraform-provisioned infra), BigQuery Agent Analytics (structured agent events for ADK agents with the plugin enabled), and third-party integrations (AgentOps, Phoenix, MLflow, and others via OpenTelemetry). Also documents the specific ordering requirement for agent_runtime deployments — provisioning infra before the first deploy — and how to retrofit observability onto an agent that was already deployed via the SDK. Does not cover deployment setup (google-agents-cli-deploy) or ADK API code patterns (google-agents-cli-adk-code).
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-observability). 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, deploy, publish) from google/agents-cli's skills/ folder.
npx skills add google/agents-cli - 2
Install the CLI itself (needed to provision the underlying infra)
Prompt-response logging and BigQuery Agent Analytics need Terraform-provisioned resources via agents-cli infra.
uv tool install google-agents-cli - 3
Activate in Claude
Ask to set up tracing, monitor a deployed agent, configure logging, or add observability.
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
Covers monitoring a deployed agent across four tiers, ordered from zero-setup to opt-in:
| Tier | What it does | Default state |
|---|---|---|
| Cloud Trace | Distributed tracing via OpenTelemetry spans | Always enabled, no infra needed |
| Prompt-Response Logging | GenAI interactions exported to GCS, BigQuery, Cloud Logging | Disabled locally, enabled when deployed |
| BigQuery Agent Analytics | Structured agent events (LLM calls, tool use, outcomes) | Opt-in via --bq-analytics at scaffold time |
| Third-Party Integrations | AgentOps, Phoenix, MLflow, and others via OpenTelemetry | Opt-in, per-provider setup |
Prompt-response logging and BigQuery Analytics both need infrastructure provisioned by agents-cli infra single-project.
A specific ordering trap it flags
For agent_runtime deployments, agents-cli infra single-project must run before the first agents-cli deploy — the Terraform module owns the whole Reasoning Engine resource, and applying it after an SDK-based deploy creates a state mismatch Terraform can’t reconcile. If you’ve already deployed via the SDK, the skill lays out two recovery paths: switch to Terraform-managed (delete and redeploy, losing in-flight sessions), or keep the SDK-deployed instance and manually grant the telemetry IAM roles Terraform would otherwise provision.
Reference files it points to
Scaffolded-project trace/logging details and env vars, the BigQuery Agent Analytics plugin (GCS offloading, tool provenance), ADK docs to fetch for more depth, and adding a user-feedback endpoint that logs to a sink feeding BigQuery.
Scope
Assumes a deployed agent — the deployment step itself is google-agents-cli-deploy. Does not cover ADK API code patterns (google-agents-cli-adk-code).