Agent Profiles
Profiles bundle model choice, prompt behavior, tool access, read-only posture, turn limits, and reasoning effort. Pick the profile that matches the job.
Built-In Profiles
Section titled “Built-In Profiles”| Profile | PromptKind | Tools | ReadOnly | MaxTurns | DefaultEffort | Use Case |
|---|---|---|---|---|---|---|
craft | chat | general coding and extension tools | false | 20 | 3 | General coding, features, bug fixes |
quick | quick | focused coding/search subset | false | 10 | 2 | Small, fast, well-defined tasks |
study | study | extended reasoning and coordination tools | false | 40 | 4 | Architecture, debugging, multi-step changes |
review | review | read-only review tools plus diagnostics | true | 12 | 3 | Code review (read-only) |
oracle | oracle | read-only investigation tools | true | 8 | 4 | Advisory second opinion (read-only) |
find | find | read, multi_read, finder, glob, grep, web_search, todo_read | true | 8 | 2 | Repository and manual/project-note discovery |
aggman | aggman | configured: find_thread, read_thread, web_search, send_message, receive_messages, todo_read, todo_write, ask_user effective: find_thread, read_thread, web_search, receive_messages, todo_read | true | 6 | 2 | Multi-agent aggregation and status synthesis |
Aliases:
| Alias | Canonical |
|---|---|
smart | craft |
rush | quick |
deep | study |
search | find |
Prompt Kinds
Section titled “Prompt Kinds”Each profile uses a promptKind that shapes the agent’s behavior:
- chat - General-purpose assistant. Balances reasoning with action.
- quick - Optimizes for small, fast tasks. Fewer tools, lower turn budget.
- study - Uses deeper reasoning for architecture, debugging, and multi-step changes.
- review - Reviews code and plans critically. Read-only posture.
- oracle - Acts as an advisory second brain. Read-only, high reasoning effort.
- find - Focuses on repository and manual/project-note discovery. Read-only.
- aggman - Receives and synthesizes coordination messages in multi-agent setups. Because the built-in profile is read-only, configured state-writing and interactive tools such as
send_message,todo_write, andask_userare filtered out of its effective registry.
Switch Profiles
Section titled “Switch Profiles”In the TUI
Section titled “In the TUI”/config- open the profile and model picker./mode- cycle throughcraft->quick->study.
From the CLI
Section titled “From the CLI”anode -x --profile study "debug this crash"anode execute --profile quick "add input validation to signup handler"anode review --profile reviewanode tools list --profile reviewThe --profile flag is wired into root -x, anode execute, daemon runs start, anode review, and anode tools inspection/use commands.
Custom Profiles
Section titled “Custom Profiles”Define custom profiles in your config.json under profiles:
{ "profiles": { "security-review": { "model": "anthropic/claude-sonnet-4-6", "promptKind": "review", "systemPrompt": "You are a security-focused code reviewer. Flag injection vulnerabilities, auth bypasses, data exposure, and unsafe deserialization. Cite CWE IDs where applicable.", "tools": ["read", "finder", "web_search", "todo_read"], "readOnly": true, "maxTurns": 15, "defaultEffort": 4 } }}Use it:
anode review --profile security-reviewProfile Fields
Section titled “Profile Fields”| Field | Type | Description |
|---|---|---|
name | string | Profile name |
model | string | Model override (e.g., "anthropic/claude-sonnet-4-6") |
promptKind | string | Prompt kind: chat, quick, study, review, oracle, find, or aggman. Aliases: rush -> quick, deep -> study, search -> find. |
promptPath | string | Path to a custom system prompt file |
systemPrompt | string | Inline custom system prompt text |
tools | string[] | Allowed tools. Supports glob patterns. ["*"] means all |
readOnly | bool | Read-only posture. Omits mutation tools from the model’s view |
maxTurns | int | Maximum model/tool turns per run |
defaultEffort | int | Default reasoning effort (1-5) |
Profile Merging
Section titled “Profile Merging”Custom profiles merge over built-in defaults. If you define a profile named quick, your fields override the built-in quick values. Missing fields keep their defaults.
Profile names are case-insensitive. When you define a new custom profile name, Anode uses craft as its merge base. When you request a profile at runtime, that name must exist as either a built-in, configured custom profile, or alias. Alias names are resolved before lookup.
Read-only profiles
Section titled “Read-only profiles”Profiles with readOnly: true omit mutation tools from the model-visible registry. The agent cannot see or call edit_file, create_file, or bash with write operations. This is enforced at the tool registry level - the model never receives these tools in its schema.
The built-in review, oracle, find, and aggman profiles are read-only.
Model Capabilities
Section titled “Model Capabilities”Each model registers capabilities that interact with profiles:
| Capability | Description |
|---|---|
SupportsReasoning | Model supports extended reasoning/thinking |
DefaultEffort | Default reasoning effort level (1-5) |
MinEffort | Minimum supported effort |
MaxEffort | Maximum supported effort |
ThinkingRequired | Model requires thinking to be enabled |
The profile’s defaultEffort is clamped to the model’s MinEffort-MaxEffort range. Cycle effort in the TUI with /effort.
Keep Going
Section titled “Keep Going”- Configuration - full settings reference including profile config
- How It Works - the agent loop and tool execution flow
- Tools - reference for all built-in tools
- Plan and Execute - structured planning with any profile