All configuration lives inDocumentation Index
Fetch the complete documentation index at: https://mintlify.com/swt-labs/vibe-better-with-claude-code-vbw/llms.txt
Use this file to discover all available pages before exploring further.
.vbw-planning/config.json. Settings are created during /vbw:init and backfilled automatically when new defaults are added in plugin updates.
Changing settings
Use/vbw:config to read or update any setting:
Run
/vbw:config with no arguments to see all current values, the active model profile, and skill-hook mappings in a single view.Settings reference
Every key inconfig/defaults.json, in order.
| Key | Default | Description |
|---|---|---|
effort | "balanced" | Planning and execution depth |
autonomy | "standard" | How often agents stop to ask |
auto_commit | true | Auto-commit after each task |
planning_tracking | "manual" | How planning artifacts are tracked |
auto_push | "never" | Auto-push after commits (never / after_phase / always) |
verification_tier | "standard" | QA depth override |
skill_suggestions | true | Show skill suggestions on init |
auto_install_skills | false | Auto-install detected skills |
discovery_questions | true | Ask discovery questions during scope |
context_compiler | true | Compile role-specific context blocks for agents |
visual_format | "unicode" | Statusline rendering (unicode / ascii) |
max_tasks_per_plan | 5 | Max tasks per plan |
prefer_teams | "auto" | When to use Agent Teams (auto / always / never) |
branch_per_milestone | false | Create a git branch per milestone |
plain_summary | true | Append plain-language phase summaries after QA |
active_profile | "default" | Active work profile (default / prototype / production / yolo / custom) |
custom_profiles | {} | User-defined named profiles (created via /vbw:profile save) |
model_profile | "quality" | Model routing profile (quality / balanced / budget) |
model_overrides | {} | Per-agent model overrides (e.g. {"dev": "opus", "qa": "haiku"}) |
worktree_isolation | "off" | Git worktree per Dev agent (off / on) |
lease_locks | true | File-level locking for concurrent agents |
token_budgets | true | Enforce per-agent token budgets |
two_phase_completion | true | Two-phase task completion verification |
metrics | true | Track and display session metrics |
smart_routing | true | Skip unnecessary agents based on effort level |
validation_gates | true | Enforce dynamic validation checkpoints |
snapshot_resume | true | Save snapshots for crash recovery |
event_recovery | true | Recover from interrupted events via event log |
monorepo_routing | true | Route commands in monorepo subdirectories |
rolling_summary | false | Maintain a rolling cross-phase context digest |
require_phase_discussion | false | Require discussion before planning begins |
auto_uat | false | Automatically run UAT after QA |
statusline_hide_limits | false | Suppress token-limit line in statusline unconditionally |
statusline_hide_limits_for_api_key | false | Suppress limit line only when using API key auth |
statusline_hide_agent_in_tmux | false | Suppress agent progress line in tmux sessions |
statusline_collapse_agent_in_tmux | false | Collapse full statusline to a single line in tmux worktree panes |
debug_logging | false | Enable verbose debug output (also: VBW_DEBUG=1 env var) |
bash_guard | true | Block destructive bash commands |
bash_guard is not stored in defaults.json — it is read directly from project config with a default of true when absent.Related pages
Effort & Autonomy
Control how deeply agents plan and how often they stop to ask.
Model Routing
Choose which Claude model each agent uses and set turn limits.
Concurrency Controls
Manage parallel Dev agents with worktrees, lease locks, and depends_on.
Commands: Supporting
Full reference for /vbw:config and /vbw:profile.