How this command is triggered — by the user, by Claude, or both
Slash command
/craft:planarch/The summary Claude sees in its command listing — used to decide when to auto-load this command
# Architecture Planning Design and plan system architecture for new features or refactoring. ## Usage ## --refine (prompt pre-processing) When `--refine` is set, do NOT act on the raw argument. First invoke the `prompt-refiner` skill with the argument and project context. Follow that skill's canonical flow (before/after → Accept/Edit/Use-original; `--yes` or auto mode auto-accepts). Then proceed using the prompt the skill returns. On no-argument interactive commands, refine AFTER the topic is captured. ## What This Does 1. **Analyzes requirements** from description 2. **Proposes arc...
Design and plan system architecture for new features or refactoring.
/craft:arch:plan <feature_or_goal>
When --refine is set, do NOT act on the raw argument. First invoke the
prompt-refiner skill with the argument and project context. Follow that
skill's canonical flow (before/after → Accept/Edit/Use-original; --yes
or auto mode auto-accepts). Then proceed using the prompt the skill
returns. On no-argument interactive commands, refine AFTER the topic is
captured.
| Output | Description |
|---|---|
| Options | 2-3 architecture approaches |
| Trade-offs | Pros/cons for each option |
| Components | Required modules/services |
| Data Model | Entity relationships |
| API Design | Endpoints and contracts |
| Dependencies | Required packages/tools |
--style <pattern> - Preferred architecture style--constraints <list> - Technical constraints--timeline <scope> - MVP vs full implementation--output <file> - Save plan to file# Plan new feature
/craft:arch:plan "user authentication with OAuth"
# Plan with constraints
/craft:arch:plan "real-time notifications" --constraints "no websockets"
# MVP scope
/craft:arch:plan "payment processing" --timeline mvp
# Save to file
/craft:arch:plan "microservices migration" --output arch-plan.md
Architecture Plan: User Authentication with OAuth
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Requirements:
- OAuth 2.0 with Google, GitHub
- Session management
- Role-based access control
Option A: Session-based (Recommended)
+ Simpler implementation
+ Works with existing stack
- Requires session storage
Option B: JWT-based
+ Stateless
+ Better for microservices
- Token refresh complexity
Components:
┌─────────────┐ ┌─────────────┐
│ Frontend │───▶│ Auth API │
└─────────────┘ └──────┬──────┘
│
┌─────────────┐ ┌──────▼──────┐
│ OAuth Providers├──│ Auth Service│
└─────────────┘ └──────┬──────┘
│
┌──────▼──────┐
│ User Store │
└─────────────┘
Implementation Steps:
1. Set up OAuth provider configs
2. Create auth service module
3. Implement callback handlers
4. Add session middleware
5. Create user model extensions
6. Add role-based decorators
7. Write integration tests
Estimated Effort: 2-3 days
Works with:
/craft:arch:analyze - Current architecture/craft:arch:diagram - Visualize plan/craft:plan:feature - Feature planning/craft:arch:review - Architecture Reviewnpx claudepluginhub data-wise/craft --plugin craft/planCreates a step-by-step implementation plan from requirements or a PRD markdown file, then waits for user confirmation before any code changes.
/planBreaks project into small verifiable tasks with acceptance criteria, dependencies, checkpoints. Reads spec/codebase, presents plan for review, saves to tasks/plan.md and tasks/todo.md.
/planStarts Manus-style file-based planning: creates task_plan.md, findings.md, progress.md if missing, invokes planning skill, and guides through workflow.
/planInteractively builds Goal, Scope, Metric, and Verify command for an autoresearch run from provided goal description.
/planRestates requirements, assesses risks, creates step-by-step implementation plan with phases, dependencies, complexity estimates, and waits for user confirmation.
/planCaptures user intent, analyzes requirements, and generates a weighted execution plan saved to .claude/session-plan.md. Does not execute — plans are saved for review or later execution via /octo:embrace.