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-craftNPX 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 ButtonCommands can take arguments:
/command:name argument1 argument2Plan 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.
| Level | Description | Example Commands |
|---|---|---|
| MANDATORY | Plan 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 |
| RECOMMENDED | Plan mode is recommended for complex scenarios. Activates when scope spans multiple modules. | /bear-workflow:plan, /bear-workflow:design, /bear-common:architecture-decision |
| CONDITIONAL | Plan 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-technologyand/bear-common:audit-*are maintainer-only (they work on the Bear Craft repository itself). Full auto-generated reference: COMMANDS-FULL-REFERENCE.
| Namespace | Technology | Count |
|---|---|---|
/common: | Transversal | 13 (10 distributed + 3 maintainer-only) |
/workflow: | Workflow (BMAD) — main path | 9 |
/team: | Agent Teams | 3 |
/qa: | QA & Testing | 5 |
/uiux: | UI/UX & Accessibility | 7 |
/symfony: | PHP/Symfony | 6 |
/flutter: | Dart/Flutter | 6 |
/python: | Python | 6 |
/react: | React/TypeScript | 6 |
/reactnative: | React Native | 6 |
/angular: | Angular | 2 |
/csharp: | C#/.NET | 2 |
/laravel: | PHP/Laravel | 2 |
/vuejs: | Vue.js | 2 |
/vite: | Vite | 3 |
/vercel: | Vercel | 2 |
/tauri: | Tauri | 1 |
/wordpress: | WordPress | 1 |
/php: | PHP | 1 |
/ruby: | Ruby / Rails | 1 |
/rust: | Rust / Axum | 1 |
/docker: | Docker/Infrastructure | 5 |
/coolify: | Coolify/PaaS | 5 |
/kubernetes: | Kubernetes/Infrastructure | 5 |
/opentofu: | OpenTofu/IaC | 5 |
/ansible: | Ansible/Automation | 5 |
/hcloud: | Hcloud/Hetzner Cloud | 5 |
/pgbouncer: | PgBouncer/Connection Pooling | 5 |
/frankenphp: | FrankenPHP/PHP Server | 5 |
/paperclip: | Paperclip AI-workforce orchestration | 4 |
/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:
| Namespace | Reference |
|---|---|
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.
| Command | Description |
|---|---|
/bear-project:backlog next story | Get next ready-for-dev story |
/bear-project:backlog move story <ID> <status> | Transition story status |
/bear-project:backlog move story --auto | Execute automatic routing rules (routing.auto_transitions, also applied after every transition) |
/bear-workflow:status | Phase, sprint metrics and next action |
/bear-workflow:implement | Sprint development |
State Machine
Stories flow through these statuses:
backlog → ready-for-dev → in-progress → review → done
↓ ↓ ↓ ↓
└─────────┴──────────────┴───────────┴→ blockedTDD 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 foundGeneration Commands
Generated files:
- src/Component/NewComponent.tsx
- src/Component/NewComponent.test.tsx
- src/Component/NewComponent.stories.tsxCheck Commands
Architecture Check
──────────────────────────────────────────────────────────────
✓ Layer separation: PASS
✗ Dependency direction: FAIL
- Infrastructure depends on Domain (src/Infra/Service.php:15)
Score: 85/100Command Frontmatter Format
All commands include YAML frontmatter for Claude Code discovery:
---
description: Brief description of what the command does
argument-hint: <required-arg> [optional-arg]
---
# Command Title
Command content...Frontmatter Fields
| Field | Required | Description |
|---|---|---|
description | Yes | Brief description shown in command list |
argument-hint | No | Shows expected arguments format |
Examples
Command with arguments:
---
description: Generate CRUD operations for an entity with Clean Architecture
argument-hint: <EntityName>
---
# Generate CRUD
Generate complete CRUD operations for $ARGUMENTS...Command without arguments:
---
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:
| Variable | Description |
|---|---|
$ARGUMENTS | All arguments passed after command name |
$ARG1, $ARG2... | Individual positional arguments |
Creating Custom Commands
Add markdown files to .claude/commands/{namespace}/:
---
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
| Principle | Action |
|---|---|
| Context is finite | Monitor context % in status line |
Use /clear | Between unrelated tasks |
| Delegate investigations | Use sub-agents (Task tool) for exploration |
| Verification loops | Always provide tests/expected outputs |
| Plan before acting | Use Plan Mode for complex tasks (> 3 files) |
| Parallel worktrees | git 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
| Mechanism | Strength | Use When |
|---|---|---|
| CLAUDE.md | Suggestion | Guidelines, conventions |
Rules (.claude/rules/) | Strong suggestion | Detailed best practices |
| Hooks | Enforcement | Security 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
- Use check commands before commits
- Generate with commands for consistent code
- Audit regularly with team-audit
- Document decisions with architecture-decision
- Track sprints with sprint commands
- Manage context — use
/clearbetween tasks, delegate investigations - Use hooks for security enforcement (not just CLAUDE.md instructions)