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 agentmods add skills/google-gemini/gemini-cli/behavioral-evalsnpx skills add google-gemini/gemini-cli --skill behavioral-evalsgit clone --depth 1 https://github.com/google-gemini/gemini-cliWhat 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 | $0.00039 | $0.00616 |
| Opus 5 | $0.00019 | $0.00308 |
| Sonnet 5 | $0.00008 | $0.00123 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
behavioral-evals 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- behavioral-evals — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Behavioral Evals
Overview
Behavioral evaluations (evals) are tests that validate the agent's decision-making (e.g., tool choice) rather than pure functionality. They are critical for verifying prompt changes, debugging steerability, and preventing regressions.
[!NOTE] Single Source of Truth: For core concepts, policies, running tests, and general best practices, always refer to evals/README.md.
🔄 Workflow Decision Tree
- Does a prompt/tool change need validation?
- No -> Normal integration tests.
- Yes -> Continue below.
- Is it UI/Interaction heavy?
- Yes -> Use
appEvalTest(AppRig). See creating.md. - No -> Use
evalTest(TestRig). See creating.md.
- Yes -> Use
- Is it a new test?
- Yes -> Set policy to
USUALLY_PASSES. - No ->
ALWAYS_PASSES(locks in regression).
- Yes -> Set policy to
- Are you fixing a failure or promoting a test?
- Fixing -> See fixing.md.
- Promoting -> See promoting.md.
📋 Quick Checklist
1. Setup Workspace
Seed the workspace with necessary files using the files object to simulate a realistic scenario (e.g., NodeJS project with package.json).
- Details in creating.md
2. Write Assertions
Audit agent decisions using rig.setBreakpoint() (AppRig only) or index verification on rig.readToolLogs().
- Details in creating.md
3. Verify
Run single tests locally with Vitest. Confirm stability locally before relying on CI workflows.
- See evals/README.md for running commands.
📦 Bundled Resources
Detailed procedural guides:
- creating.md: Assertion strategies, Rig selection, Mock MCPs.
- fixing.md: Step-by-step automated investigation, architecture diagnosis guidelines.
- promoting.md: Candidate identification criteria and threshold guidelines.
What ships with it
6 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.
- yesterday First seen · 57 lines · 39 tokens per session scan A c1ab849bb3b1
behavioral-evals is a skill published in the GitHub repository google-gemini/gemini-cli (106,749 stars, last pushed 2d ago), licensed Apache-2.0. It adds 39 tokens to every session and 616 once invoked, about $0.0002 per session on Opus 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
gemini-omni-flash-api
Use this skill for generative video editing, text-to-video, image-referenced video generation, first-frame-to-video, first-and-last-frame transitions, and video extensions using Gemini Omni 1.1 Flash (gemini-omni-1.1-flash) via the official google-genai SDK. Includes workflows for pre-processing/optimizing…
gemini-interactions-api
Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, streaming responses, background research tasks, function calling, structured output, or migrating from the old generateContent API. This skill covers the…
gemini-live-api-dev
Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API. Covers WebSocket-based audio/video/text streaming, voice activity detection (VAD), native audio features, function calling, session management, ephemeral tokens for client-side auth, live translation, and all Live…
gemini-api-dev
Use this skill when building applications with Gemini API hosted models, including Gemini and Gemma 4, working with multimodal content (text, images, audio, video), implementing function calling, using structured outputs, or needing current model specifications. Covers SDK usage (google-genai for Python, @google/genai…
google-antigravity-sdk
Design, implement, and debug autonomous AI agents and multi-agent systems using the Google Antigravity (AGY) SDK. ACTIVATE this skill when the user wants to create, configure, or orchestrate Google Antigravity agents.
gemini-skill
通过 Gemini 官网（gemini.google.com）执行生图、对话等操作。用户提到"生图/画图/绘图/nano banana/nanobanana/生成图片"等关键词时触发。操作方式分三级优先级：首选 MCP 工具 → 次选 Skill 脚本 → 最次连接 Skill 浏览器手动操作（需用户授权）。禁止自行启动外部浏览器访问 Gemini。.