Deep Planning
deep_planningManages multi-phase planning sessions by moving through init, clarify, explore, evaluate, and finalize phases, tracking reasoning state for structured problem-solving.
Instructions
A structured planning tool that manages multi-phase planning sessions. Complements sequential_thinking by tracking planning state while the LLM reasons deeply.
Workflow: init → clarify → explore → evaluate → finalize
init: Define the problem, context, and constraints
clarify: Record clarifying questions and answers (repeatable)
explore: Record approach branches with pros/cons (repeatable)
evaluate: Score approaches on feasibility, completeness, coherence, risk (repeatable)
finalize: Select best approach and generate structured implementation plan
Each phase returns valid next phases to guide the workflow. Complex fields (pros, cons, steps, risks, constraints) are passed as JSON strings.
Use sequential_thinking for deep reasoning between phases. Use deep_planning to record conclusions and track planning state.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cons | No | JSON array of disadvantage strings | |
| name | No | Short approach name (required for explore) | |
| pros | No | JSON array of advantage strings | |
| risk | No | Risk score 0-10 (lower is better) | |
| phase | Yes | Current planning phase | |
| risks | No | JSON array of risk objects with description and mitigation | |
| steps | No | JSON array of implementation step objects | |
| answer | No | Answer to the clarifying question | |
| format | No | Output format: markdown (default) or json | |
| context | No | Additional background context | |
| problem | No | Problem statement (required for init) | |
| branchId | No | Unique approach identifier (required for explore/evaluate) | |
| planName | No | Descriptive plan name (init phase only). Sanitized to kebab-case. Generates dp-YYYYMMDD-{name} session ID. | |
| question | No | Clarifying question (required for clarify) | |
| coherence | No | Coherence score 0-10 | |
| rationale | No | Reasoning for evaluation scores | |
| sessionId | No | Resume a specific session by ID. Required when switching between multiple sessions. Ignored on init phase. | |
| assumptions | No | JSON array of assumption strings | |
| constraints | No | JSON array of constraint strings | |
| description | No | Detailed approach description | |
| feasibility | No | Feasibility score 0-10 | |
| completeness | No | Completeness score 0-10 | |
| recommendation | No | pursue, refine, or abandon | |
| selectedBranch | No | Branch ID of chosen approach (required for finalize) | |
| successCriteria | No | JSON array of success criteria strings |