docs/configuration-customisation/agent-configurations.mdx
Agent profiles let you define multiple named variants for each supported coding agent. Variants capture configuration differences like planning mode, model choice, and sandbox permissions that you can quickly select when creating attempts.
<Info> Agent profiles are used throughout Vibe Kanban wherever agents run: onboarding, default settings, attempt creation, and follow-ups. </Info>You can configure agent profiles in two ways through Settings → Agents:
<Tabs> <Tab title="Form Editor"> Use the guided interface with form fields for each agent setting. <Frame> </Frame> </Tab> <Tab title="JSON Editor"> Edit the underlying `profiles.json` file directly for advanced configurations. <Frame> </Frame> </Tab> </Tabs> <Note> The configuration page displays the exact file path where your settings are stored. Vibe Kanban saves only your overrides whilst preserving built-in defaults. </Note>The profiles configuration uses a JSON structure with an executors object containing agent variants:
{
"executors": {
"CLAUDE_CODE": {
"DEFAULT": { "CLAUDE_CODE": { "dangerously_skip_permissions": true } },
"PLAN": { "CLAUDE_CODE": { "plan": true } },
"ROUTER": { "CLAUDE_CODE": { "claude_code_router": true, "dangerously_skip_permissions": true } }
},
"GEMINI": {
"DEFAULT": { "GEMINI": { "model": "default", "yolo": true } },
"FLASH": { "GEMINI": { "model": "flash", "yolo": true } }
},
"CODEX": {
"DEFAULT": { "CODEX": { "sandbox": "danger-full-access" } },
"HIGH": { "CODEX": { "sandbox": "danger-full-access", "model_reasoning_effort": "high" } }
}
}
}
View full CLI reference → </Tab>
<Tab title="GEMINI"> <ParamField path="model" type="string"> Choose model variant: `"default"` or `"flash"` </ParamField> <ParamField path="yolo" type="boolean"> Run without confirmations </ParamField>View full CLI reference → </Tab>
<Tab title="AMP"> <ParamField path="dangerously_allow_all" type="boolean"> Allow all actions without restrictions (unsafe) </ParamField>View full documentation → </Tab>
<Tab title="CODEX"> <ParamField path="sandbox" type="string"> Execution environment: `"read-only"`, `"workspace-write"`, or `"danger-full-access"` </ParamField> <ParamField path="approval" type="string"> Approval level: `"untrusted"`, `"on-failure"`, `"on-request"`, or `"never"` </ParamField> <ParamField path="model_reasoning_effort" type="string"> Reasoning depth: `"low"`, `"medium"`, or `"high"` </ParamField> <ParamField path="model_reasoning_summary" type="string"> Summary style: `"auto"`, `"concise"`, `"detailed"`, or `"none"` </ParamField>View full documentation → </Tab>
<Tab title="CURSOR"> <ParamField path="force" type="boolean"> Force execution without confirmation </ParamField> <ParamField path="model" type="string"> Specify model to use </ParamField>View full CLI reference → </Tab>
<Tab title="OPENCODE"> <ParamField path="model" type="string"> Specify model to use </ParamField> <ParamField path="agent" type="string"> Choose agent type </ParamField>View full documentation → </Tab>
<Tab title="QWEN_CODE"> <ParamField path="yolo" type="boolean"> Run without confirmations </ParamField>View full documentation → </Tab>
<Tab title="DROID"> <ParamField path="autonomy" type="string"> Permission level: `"normal"`, `"low"`, `"medium"`, `"high"`, or `"skip-permissions-unsafe"` </ParamField> <ParamField path="model" type="string"> Specify which model to use </ParamField> <ParamField path="reasoning_effort" type="string"> Reasoning depth: `"off"`, `"low"`, `"medium"`, or `"high"` </ParamField>View full documentation → </Tab> </Tabs>
These options work across multiple agent types:
<ParamField path="append_prompt" type="string | null"> Text appended to the system prompt </ParamField> <ParamField path="base_command_override" type="string | null"> Override the underlying CLI command </ParamField> <ParamField path="additional_params" type="string[] | null"> Additional CLI arguments to pass </ParamField> <Warning> Options prefixed with "dangerously_" bypass safety confirmations and can perform destructive actions. Use with extreme caution. </Warning>