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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/google/agents-clinpx agentmods add skills/google/agents-cli/google-agents-cli-evalWrote 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-eval)<a href="https://agentmods.dev/skills/google/agents-cli/google-agents-cli-eval"><img src="https://agentmods.dev/badge/skills/google/agents-cli/google-agents-cli-eval/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-eval"><img src="https://agentmods.dev/badge/skills/google/agents-cli/google-agents-cli-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00149 | $0.05729 |
| Opus 5.5 | $0.00060 | $0.02292 |
| Sonnet 5.5 | $0.00030 | $0.01146 |
| Haiku 4.5 | $0.00015 | $0.00573 |
Grade A, and why
google-agents-cli-eval scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Evaluation Guide
Requires:
agents-cli(uv tool install google-agents-cli) — install uv first if needed.
Scaffolded project? If you used
/google-agents-cli-scaffold, dataset and a custom metric are already scaffolded intests/eval/(Python projects) oreval/(Go projects). For simplicity, this skill and its references use the Python directory layout; adjust accordingly if you've scaffolded a Go agent. You already haveagents-cli eval run(chainsgenerate+grade),tests/eval/datasets/, andtests/eval/eval_config.yaml. Start with executingeval runand iterate from there.
Reference Files
| File | Contents |
|---|---|
references/dataset_schema.md |
Canonical EvaluationDataset schema — all field types, JSON examples for single-turn / multi-turn / multi-agent, common mistakes |
references/metrics-guide.md |
Complete metrics reference — all built-in metrics, match types, custom metrics, judge model config |
references/user-simulation.md |
Dynamic conversation testing — eval dataset synthesize flags, what scenarios are, compatible metrics |
references/builtin-tools-eval.md |
google_search and model-internal tools — trajectory behavior, metric compatibility |
references/advanced-commands.md |
Opt-in commands: eval analyze, eval optimize, eval submit / eval results |
references/multimodal-eval.md |
Multimodal inputs — eval dataset schema, built-in metric limitations, custom evaluator pattern |
references/live-eval.md |
Live and voice agents — --mode adk_live, what gets graded, user-only turn authoring, the Live-model and region traps |
The Quality Flywheel
Improving agent quality is iterative. The 4 stages below describe the loop. Each stage has a Default path (you, the coding agent, do the work directly) and an Opt-in CLI command that delegates to the Eval Service in Gemini platform for better quality and scale.
What ships with it
7 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 02b07ebb1419
- 9d ago Changed 8345488b87a0
- 15d ago Changed 4d4a12aa9f71
- 23d ago Changed · +13 lines 00dac958fb45
- 29d ago Changed · +1 lines 11b4784d9736
- 1mo ago Changed · +13 lines · +24 tokens per session e5b00d959783
- 1mo ago First seen · 365 lines · 125 tokens per session scan A d38c9792ec73
google-agents-cli-eval is a skill published in the GitHub repository google/agents-cli (6,094 stars, last pushed 4d ago), licensed Apache-2.0. It adds 149 tokens to every session and 5,729 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
adk-student-evaluator
Acts as a student developer to evaluate ADK training modules. Follows a rigorous 5-step workflow to test labs and generate formal pedagogical reports. Use when asked to "evaluate", "test as a student", or "review" a training module.
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
potpie-project-preferences
Use before writing, modifying, reviewing, refactoring, or testing code so repo/project preferences surface: error handling, file structure, frameworks, logging, dependency choices, testing, security, API style, and naming. Also use after code work when a reusable project preference should be recorded.
guardrails-developer-create-guardrails
Helps developers create a NeMo Guardrails configuration for an LLM application. Use when users want to build, scaffold, configure, test, or iterate on input, output, retrieval, dialog, execution, Colang, or catalog-based guardrails. Trigger keywords - create guardrails, build guardrails, scaffold config, write rails…
qa-expert
Expert-level quality assurance, testing strategies, automation, and QA processes. Use when the user mentions testing, test automation, quality assurance, or Selenium, or when the task involves Testing Types, QA Processes, Test Strategy, or Defect Management.