Subagents

Subagents are specialized agents that operate within your main Gemini CLI session. They are designed to handle specific, complex tasks—like deep codebase analysis, documentation lookup, or domain-specific reasoning—without cluttering the main agent’s context or toolset.

Subagents are enabled by default. To disable them, set enableAgents to false in your settings.json:

{
  "experimental": { "enableAgents": false }
}

Subagents are “specialists” that the main Gemini agent can hire for a specific job.

• Focused context: Each subagent has its own system prompt and persona.
• Specialized tools: Subagents can have a restricted or specialized set of tools.
• Independent context window: Interactions with a subagent happen in a separate context loop, which saves tokens in your main conversation history.

Subagents are exposed to the main agent as a tool of the same name. When the main agent calls the tool, it delegates the task to the subagent. Once the subagent completes its task, it reports back to the main agent with its findings.

You can use subagents through automatic delegation or by explicitly forcing them in your prompt.

Gemini CLI’s main agent is instructed to use specialized subagents when a task matches their expertise. For example, if you ask “How does the auth system work?”, the main agent may decide to call the codebase_investigator subagent to perform the research.

You can explicitly direct a task to a specific subagent by using the @ symbol followed by the subagent’s name at the beginning of your prompt. This is useful when you want to bypass the main agent’s decision-making and go straight to a specialist.

Example:

@codebase_investigator Map out the relationship between the AgentRegistry and the LocalAgentExecutor.

When you use the @ syntax, the CLI injects a system note that nudges the primary model to use that specific subagent tool immediately.

Gemini CLI comes with the following built-in subagents:

• Name: codebase_investigator
• Purpose: Analyze the codebase, reverse engineer, and understand complex dependencies.
• When to use: “How does the authentication system work?”, “Map out the dependencies of the AgentRegistry class.”
• Configuration: Enabled by default. You can override its settings in settings.json under agents.overrides. Example (forcing a specific model and increasing turns):

  {
    "agents": {
      "overrides": {
        "codebase_investigator": {
          "modelConfig": { "model": "gemini-3-flash-preview" },
          "runConfig": { "maxTurns": 50 }
        }
      }
    }
  }

• Name: cli_help
• Purpose: Get expert knowledge about Gemini CLI itself, its commands, configuration, and documentation.
• When to use: “How do I configure a proxy?”, “What does the /rewind command do?”
• Configuration: Enabled by default.

• Name: generalist_agent
• Purpose: Route tasks to the appropriate specialized subagent.
• When to use: Implicitly used by the main agent for routing. Not directly invoked by the user.
• Configuration: Enabled by default. No specific configuration options.

• Name: browser_agent
• Purpose: Automate web browser tasks — navigating websites, filling forms, clicking buttons, and extracting information from web pages — using the accessibility tree.
• When to use: “Go to example.com and fill out the contact form,” “Extract the pricing table from this page,” “Click the login button and enter my credentials.”

The browser agent requires:

• Chrome version 144 or later (any recent stable release will work).
• Node.js with npx available (used to launch the chrome-devtools-mcp server).

The browser agent is disabled by default. Enable it in your settings.json:

{
  "agents": {
    "overrides": {
      "browser_agent": {
        "enabled": true
      }
    }
  }
}

The sessionMode setting controls how Chrome is launched and managed. Set it under agents.browser:

{
  "agents": {
    "overrides": {
      "browser_agent": {
        "enabled": true
      }
    },
    "browser": {
      "sessionMode": "persistent"
    }
  }
}

The available modes are:

All browser-specific settings go under agents.browser in your settings.json.

The browser agent enforces the following security restrictions:

• Blocked URL patterns: file://, javascript:, data:text/html, chrome://extensions, and chrome://settings/passwords are always blocked.
• Sensitive action confirmation: Actions like form filling, file uploads, and form submissions require user confirmation through the standard policy engine.

By default, the browser agent interacts with pages through the accessibility tree using element uid values. For tasks that require visual identification (for example, “click the yellow button” or “find the red error message”), you can enable the visual agent by setting a visualModel:

{
  "agents": {
    "overrides": {
      "browser_agent": {
        "enabled": true
      }
    },
    "browser": {
      "visualModel": "gemini-2.5-computer-use-preview-10-2025"
    }
  }
}

When enabled, the agent gains access to the analyze_screenshot tool, which captures a screenshot and sends it to the vision model for analysis. The model returns coordinates and element descriptions that the browser agent uses with the click_at tool for precise, coordinate-based interactions.

The browser agent adjusts its behavior automatically when running inside a sandbox.

When the CLI runs under the macOS seatbelt sandbox, persistent and isolated session modes are forced to isolated with headless enabled. This avoids permission errors caused by seatbelt file-system restrictions on persistent browser profiles. If sessionMode is set to existing, no override is applied.

Chrome is not available inside the container, so the browser agent is disabled unless sessionMode is set to "existing". When enabled with existing mode, the agent automatically connects to Chrome on the host via the resolved IP of host.docker.internal:9222 instead of using local pipe discovery. Port 9222 is currently hardcoded and cannot be customized.

To use the browser agent in a Docker sandbox:

1. Start Chrome on the host with remote debugging enabled:

   # Option A: Launch Chrome from the command line
   google-chrome --remote-debugging-port=9222
   
   # Option B: Enable in Chrome settings
   # Navigate to chrome://inspect/#remote-debugging and enable

2. Configure sessionMode and allowed domains in your project’s .gemini/settings.json:

   {
     "agents": {
       "overrides": {
         "browser_agent": { "enabled": true }
       },
       "browser": {
         "sessionMode": "existing",
         "allowedDomains": ["example.com"]
       }
     }
   }

3. Launch the CLI with port forwarding:

   GEMINI_SANDBOX=docker SANDBOX_PORTS=9222 gemini

You can create your own subagents to automate specific workflows or enforce specific personas.

Custom agents are defined as Markdown files (.md) with YAML frontmatter. You can place them in:

1. Project-level: .gemini/agents/*.md (Shared with your team)
2. User-level: ~/.gemini/agents/*.md (Personal agents)

The file MUST start with YAML frontmatter enclosed in triple-dashes ---. The body of the markdown file becomes the agent’s System Prompt.

Example: .gemini/agents/security-auditor.md

---
name: security-auditor
description: Specialized in finding security vulnerabilities in code.
kind: local
tools:
  - read_file
  - grep_search
model: gemini-3-flash-preview
temperature: 0.2
max_turns: 10
---

You are a ruthless Security Auditor. Your job is to analyze code for potential
vulnerabilities.

Focus on:

1.  SQL Injection
2.  XSS (Cross-Site Scripting)
3.  Hardcoded credentials
4.  Unsafe file operations

When you find a vulnerability, explain it clearly and suggest a fix. Do not fix
it yourself; just report it.

When defining tools for a subagent, you can use wildcards to quickly grant access to groups of tools:

• *: Grant access to all available built-in and discovered tools.
• mcp_*: Grant access to all tools from all connected MCP servers.
• mcp_my-server_*: Grant access to all tools from a specific MCP server named my-server.

Each subagent runs in its own isolated context loop. This means:

• Independent history: The subagent’s conversation history does not bloat the main agent’s context.
• Isolated tools: The subagent only has access to the tools you explicitly grant it.
• Recursion protection: To prevent infinite loops and excessive token usage, subagents cannot call other subagents. If a subagent is granted the * tool wildcard, it will still be unable to see or invoke other agents.

Subagent tool isolation moves Gemini CLI away from a single global tool registry. By providing isolated execution environments, you can ensure that subagents only interact with the parts of the system they are designed for. This prevents unintended side effects, improves reliability by avoiding state contamination, and enables fine-grained permission control.

With this feature, you can:

• Specify tool access: Define exactly which tools an agent can access using a tools list in the agent definition.
• Define inline MCP servers: Configure Model Context Protocol (MCP) servers (which provide a standardized way to connect AI models to external tools and data sources) directly in the subagent’s markdown frontmatter, isolating them to that specific agent.
• Maintain state isolation: Ensure that subagents only interact with their own set of tools and servers, preventing side effects and state contamination.
• Apply subagent-specific policies: Enforce granular rules in your Policy Engine TOML configuration based on the executing subagent’s name.

You can configure tool isolation for a subagent by updating its markdown frontmatter. This allows you to explicitly state which tools the subagent can use, rather than relying on the global registry.

Add an mcpServers object to define inline MCP servers that are unique to the agent.

Example:

---
name: my-isolated-agent
tools:
  - grep_search
  - read_file
mcpServers:
  my-custom-server:
    command: 'node'
    args: ['path/to/server.js']
---

You can enforce fine-grained control over subagents using the Policy Engine’s TOML configuration. This allows you to grant or restrict permissions specifically for an agent, without affecting the rest of your CLI session.

To restrict a policy rule to a specific subagent, add the subagent property to the [[rules]] block in your policy.toml file.

Example:

[[rules]]
name = "Allow pr-creator to push code"
subagent = "pr-creator"
description = "Permit pr-creator to push branches automatically."
action = "allow"
toolName = "run_shell_command"
commandPrefix = "git push"

In this configuration, the policy rule only triggers if the executing subagent’s name matches pr-creator. Rules without the subagent property apply universally to all agents.

You can manage subagents interactively using the /agents command or persistently via settings.json.

If you are in an interactive CLI session, you can use the /agents command to manage subagents without editing configuration files manually. This is the recommended way to quickly enable, disable, or re-configure agents on the fly.

For a full list of sub-commands and usage, see the /agents command reference.

While the /agents command and agent definition files provide a starting point, you can use settings.json for global, persistent overrides. This is useful for enforcing specific models or execution limits across all sessions.

Use this to enable or disable specific agents or override their run configurations.

{
  "agents": {
    "overrides": {
      "security-auditor": {
        "enabled": false,
        "runConfig": {
          "maxTurns": 20,
          "maxTimeMinutes": 10
        }
      }
    }
  }
}

You can target specific subagents with custom model settings (like system instruction prefixes or specific safety settings) using the overrideScope field.

{
  "modelConfigs": {
    "overrides": [
      {
        "match": { "overrideScope": "security-auditor" },
        "modelConfig": {
          "generateContentConfig": {
            "temperature": 0.1
          }
        }
      }
    ]
  }
}

The main agent’s system prompt encourages it to use an expert subagent when one is available. It decides whether an agent is a relevant expert based on the agent’s description. You can improve the reliability with which an agent is used by updating the description to more clearly indicate:

• Its area of expertise.
• When it should be used.
• Some example scenarios.

For example, the following subagent description should be called fairly consistently for Git operations.

Git expert agent which should be used for all local and remote git operations. For example:

• Making commits
• Searching for regressions with bisect
• Interacting with source control and issues providers such as GitHub.

If you need to further tune your subagent, you can do so by selecting the model to optimize for with /model and then asking the model why it does not think that your subagent was called with a specific prompt and the given description.

Gemini CLI can also delegate tasks to remote subagents using the Agent-to-Agent (A2A) protocol.

See the Remote Subagents documentation for detailed configuration, authentication, and usage instructions.

Extensions can bundle and distribute subagents. See the Extensions documentation for details on how to package agents within an extension.