plan
v2.88 Key Changes (MODEL-AGNOSTIC)
- Model-agnostic: Uses model configured in
~/.claude/settings.jsonor CLI/env vars - No flags required: Works with the configured default model
- Flexible: Works with GLM-5, Claude, Minimax, or any configured model
- Settings-driven: Model selection via
ANTHROPIC_DEFAULT_*_MODELenv vars
Plan-State Management
Create, track, and manage implementation plans with Lead Software Architect verification.
Subcommands
init - Initialize new plan
/plan init "Implement user authentication"
Creates .claude/plan-state.json with:
- Task title, phases, risk level
- File modifications list
- Test strategy
- Validation criteria
status - Show plan status
/plan status
Displays:
- Current phase
- Completed vs pending steps
- Overall progress percentage
- Next action required
add-step - Add implementation step
/plan add-step "Create User model with validation"
Appends step to phases array with:
- Step description
- Assigned agent/model
- Dependencies
- Validation criteria
start - Begin implementation
/plan start
Triggers:
- LSA pre-verification
- Plan-Sync monitoring activation
- First phase execution
complete - Mark step complete
/plan complete --step 2
Updates plan-state.json and logs completion in ledger.
verify - Verify plan completion
/plan verify
Runs full validation against requirements:
- LSA architecture check
- Quality gate verification
- Requirements coverage
sync - Synchronize with execution
/plan sync
Detects drift between plan and execution, patches downstream references.
Workflow
/plan init "Feature description"
↓ (creates plan-state.json)
/plan add-step "Step 1"
/plan add-step "Step 2"
↓
/plan start
↓ (LSA verification)
/plan complete --step 1
/plan complete --step 2
↓
/plan verify
↓
VERIFIED_DONE
Output Examples
Plan Status Output
========================================
PLAN STATE: Feature Implementation
========================================
Status: In Progress
Phase: 2/4 - Backend Implementation
Progress: 45%
Steps:
✅ 1. Database Schema - COMPLETE
⏳ 2. API Endpoints - IN PROGRESS
🔲 3. Frontend Integration
🔲 4. Testing & Validation
Next Action: /plan complete --step 2
========================================
Related Skills
/orchestrator- Full orchestration with plan integration/iterate- Iterative execution following plan steps/gates- Quality validation at plan milestones/retrospective- Post-completion analysis
More from alfredolopez80/multi-agent-ralph-loop
stop-slop
A skill for removing AI-generated writing patterns ('slop') from prose. Eliminates telltale signs of AI writing like filler phrases, excessive hedging, overly formal language, and mechanical sentence structures. Use when: writing content that should sound human and natural, editing AI-generated drafts, cleaning up prose for publication, or any content that needs to sound authentic rather than AI-generated. Triggers: 'stop-slop', 'remove AI tells', 'clean up prose', 'make it sound human', 'edit AI writing'.
10iterate
Ralph Loop pattern with swarm mode: iterative execution until VERIFIED_DONE with multi-agent coordination. Use when: (1) iterative refinement needed, (2) quality gates must pass, (3) automated validation required. Triggers: /iterate, 'iterate until done', 'keep trying', 'fix until passing', 'loop until done'.
2gemini-cli
|
2minimax
Custom skill for minimax
1clarify
Intensive requirement clarification using structured AskUserQuestion workflow. Gathers MUST_HAVE (blocking) and NICE_TO_HAVE (optional) information before implementation. Use when: (1) starting new feature implementation, (2) requirements are ambiguous, (3) multiple approaches possible, (4) before writing any code. Triggers: /clarify, 'clarify requirements', 'ask questions', 'gather requirements'.
1security
Security audit with Codex + MiniMax second opinion. Integrates ralph-security agent (6 quality pillars, OWASP A01-A10). Uses LSP for code navigation during analysis. Use when: (1) /security is invoked, (2) task relates to security functionality.
1