Skip to content

Commands Reference ​

This is the narrated, namespace-grouped reference (active commands only; the commands removed in 9.0 are listed in MIGRATION-v9.md). For the complete auto-generated table of all 197 command files (core + infra, with source links), see COMMANDS-FULL-REFERENCE.md. For the bear-craft NPX CLI (a different tool — install, init, check…), see CLI-REFERENCE.md.

Claude Code commands are slash commands that automate workflows and provide structured assistance.

How to Use Commands ​

Type a slash command in Claude Code:

/bear-gate:check commit
/bear-symfony:generate-crud User
/bear-react:generate-component Button

Commands can take arguments:

/command:name argument1 argument2

Plan Mode Classification ​

Every command includes a Plan Mode section that indicates when Claude should activate plan mode before executing. This ensures proper analysis and validation for impactful operations.

LevelDescriptionExample Commands
MANDATORYPlan mode activates automatically before execution. Claude analyzes impacted code and proposes a plan for your validation./bear-workflow:implement, /bear-qa:tdd, /bear-qa:recette, generate-* commands
RECOMMENDEDPlan mode is recommended for complex scenarios. Activates when scope spans multiple modules./bear-workflow:plan, /bear-workflow:design, /bear-common:architecture-decision
CONDITIONALPlan mode activates automatically when scope is broad (multiple modules, cross-cutting analysis).check-* commands, /bear-workflow:plan --research

Tip: Commands without a Plan Mode section (e.g., /bear-workflow:status, /bear-workflow:status --standup) are lightweight and never require plan mode.


Command Namespaces ​

The generated reference lists 135 commands across all namespaces (infra and project management included). The counts below are the commands of the 18 namespaces. /bear-common:add-technology and /bear-common:audit-* are maintainer-only (they work on the Bear Craft repository itself). Full auto-generated reference: COMMANDS-FULL-REFERENCE.

NamespaceTechnologyCount
/common:Transversal13 (10 distributed + 3 maintainer-only)
/workflow:Workflow (BMAD) — main path9
/team:Agent Teams3
/qa:QA & Testing5
/uiux:UI/UX & Accessibility7
/symfony:PHP/Symfony6
/flutter:Dart/Flutter6
/python:Python6
/react:React/TypeScript6
/reactnative:React Native6
/angular:Angular2
/csharp:C#/.NET2
/laravel:PHP/Laravel2
/vuejs:Vue.js2
/vite:Vite3
/vercel:Vercel2
/tauri:Tauri1
/wordpress:WordPress1
/php:PHP1
/ruby:Ruby / Rails1
/rust:Rust / Axum1
/docker:Docker/Infrastructure5
/coolify:Coolify/PaaS5
/kubernetes:Kubernetes/Infrastructure5
/opentofu:OpenTofu/IaC5
/ansible:Ansible/Automation5
/hcloud:Hcloud/Hetzner Cloud5
/pgbouncer:PgBouncer/Connection Pooling5
/frankenphp:FrankenPHP/PHP Server5
/paperclip:Paperclip AI-workforce orchestration4
/gate:Quality Gates (BMAD v6)1 (/bear-gate:check, 11 modes)
/project:Project Management (BMAD v6)5

Command Reference by Namespace ​

Each namespace has its own focused page:

NamespaceReference
Common Commands (/common:)View commands
Workflow Commands (/workflow:)View commands
Symfony Commands (/symfony:)View commands
Flutter Commands (/flutter:)View commands
Python Commands (/python:)View commands
React Commands (/react:)View commands
React Native Commands (/reactnative:)View commands
Angular Commands (/angular:)View commands
C#/.NET Commands (/csharp:)View commands
Laravel Commands (/laravel:)View commands
Vue.js Commands (/vuejs:)View commands
Vite Commands (/vite:)View commands
Vercel Commands (/vercel:)View commands
Ruby / Rails Commands (/ruby:)View commands
Rust / Axum Commands (/rust:)View commands
Tauri Commands (/tauri:)View commands
WordPress Commands (/wordpress:)View commands
PHP Commands (/php:)View commands
Docker Commands (/docker:)View commands
Coolify Commands (/coolify:)View commands
Kubernetes Commands (/kubernetes:)View commands
OpenTofu Commands (/opentofu:)View commands
Ansible Commands (/ansible:)View commands
Hcloud Commands (/hcloud:)View commands
PgBouncer Commands (/pgbouncer:)View commands
FrankenPHP Commands (/frankenphp:)View commands
Paperclip Commands (/paperclip:)View commands
Project Commands (/project:)View commands
Quality Gate Commands (/gate:)View commands
QA Recette Commands (/qa:)View commands

Sprint Status Commands ​

Story routing lives in /bear-project:backlog; status is read with /bear-workflow:status.

CommandDescription
/bear-project:backlog next storyGet next ready-for-dev story
/bear-project:backlog move story <ID> <status>Transition story status
/bear-project:backlog move story --autoExecute automatic routing rules (routing.auto_transitions, also applied after every transition)
/bear-workflow:statusPhase, sprint metrics and next action
/bear-workflow:implementSprint development

State Machine ​

Stories flow through these statuses:

backlog → ready-for-dev → in-progress → review → done
    ↓         ↓              ↓           ↓
    └─────────┴──────────────┴───────────┴→ blocked

TDD Phase Tracking:

  • 🔴 red - Writing failing tests
  • 🟢 green - Implementing to pass
  • 🔵 refactor - Cleaning up code

Removed commands (9.0) ​

The 52 deprecated PM commands and the whole sprint namespace were removed in 9.0, together with /bear-common:research-context7 and /bear-uiux:orchestrator (deprecated in 8.27.0). See MIGRATION-v9.md for the complete old → new table.

Removed commands (10.0) ​

The 66 redirect stubs deprecated in 9.0 were removed in 10.0: the five per-axis commands of each of the 13 stacks that had them (angular, csharp, flutter, laravel, paperclip, php, python, react, reactnative, symfony, vercel, vite, vuejs) and the sprint command of the team namespace. See MIGRATION-v10.md for the old → new table. The per-axis checklists are installed in .claude/references/<tech>/checks/.


Command Output Formats ​

Commands typically output in structured formats:

Audit Commands ​

══════════════════════════════════════════════════════════════
AUDIT REPORT
══════════════════════════════════════════════════════════════

[ ] Issue 1
[x] Check passed
[ ] Issue 2

Summary: 2 issues found

Generation Commands ​

Generated files:
- src/Component/NewComponent.tsx
- src/Component/NewComponent.test.tsx
- src/Component/NewComponent.stories.tsx

Check Commands ​

Architecture Check
──────────────────────────────────────────────────────────────
✓ Layer separation: PASS
✗ Dependency direction: FAIL
  - Infrastructure depends on Domain (src/Infra/Service.php:15)

Score: 85/100

Command Frontmatter Format ​

All commands include YAML frontmatter for Claude Code discovery:

markdown
---
description: Brief description of what the command does
argument-hint: <required-arg> [optional-arg]
---

# Command Title

Command content...

Frontmatter Fields ​

FieldRequiredDescription
descriptionYesBrief description shown in command list
argument-hintNoShows expected arguments format

Examples ​

Command with arguments:

markdown
---
description: Generate CRUD operations for an entity with Clean Architecture
argument-hint: <EntityName>
---

# Generate CRUD

Generate complete CRUD operations for $ARGUMENTS...

Command without arguments:

markdown
---
description: Run all pre-commit checks (tests, lint, security)
---

# Pre-Commit Check

Execute all validation checks before committing...

Variable Substitution ​

Commands can use these variables:

VariableDescription
$ARGUMENTSAll arguments passed after command name
$ARG1, $ARG2...Individual positional arguments

Creating Custom Commands ​

Add markdown files to .claude/commands/{namespace}/:

markdown
---
description: What this command does
argument-hint: <arg1> [arg2]
---

# My Custom Command

Description of what this command does.

## Arguments
$ARGUMENTS

## Process

### Step 1
What to do first...

### Step 2
What to do next...

## Output
Expected output format...

Place in:

  • .claude/commands/bear-common/ for /common: namespace
  • .claude/commands/myproject/ for /myproject: namespace

Context Management Best Practices ​

Effective context management is the #1 productivity factor with Claude Code (source: Anthropic).

Key Principles ​

PrincipleAction
Context is finiteMonitor context % in status line
Use /clearBetween unrelated tasks
Delegate investigationsUse sub-agents (Task tool) for exploration
Verification loopsAlways provide tests/expected outputs
Plan before actingUse Plan Mode for complex tasks (> 3 files)
Parallel worktreesgit worktree add for concurrent sessions

CLAUDE.md Size ​

Keep your main CLAUDE.md under 200 lines. Each additional instruction dilutes attention on existing ones. Use .claude/rules/ for detailed guidelines.

Hooks vs Instructions ​

MechanismStrengthUse When
CLAUDE.mdSuggestionGuidelines, conventions
Rules (.claude/rules/)Strong suggestionDetailed best practices
HooksEnforcementSecurity constraints, formatting

See Dev/i18n/base/Common/hooks/templates/examples/ for ready-to-use hook templates.

Context Thresholds ​

Context %Recommended Action
< 30%Normal operation
30-60%Monitor, avoid unnecessary file reads
60-80%Delegate to sub-agents, consider /clear
> 80%Compaction imminent, save critical context

See rule 12-context-management.md for full documentation.


Best Practices ​

  1. Use check commands before commits
  2. Generate with commands for consistent code
  3. Audit regularly with team-audit
  4. Document decisions with architecture-decision
  5. Track sprints with sprint commands
  6. Manage context — use /clear between tasks, delegate investigations
  7. Use hooks for security enforcement (not just CLAUDE.md instructions)