Skip to main content
Glama

create_plan

Generate structured implementation plans for software development tasks by analyzing codebase context, identifying dependencies and risks, and creating actionable step-by-step guides.

Instructions

Generate a detailed implementation plan for a software development task.

This tool enters Planning Mode, where it:

  1. Analyzes the codebase context relevant to your task

  2. Generates a structured, actionable implementation plan

  3. Identifies dependencies, risks, and parallelization opportunities

  4. Creates architecture diagrams when helpful

When to use this tool:

  • Before starting a complex feature or refactoring task

  • When you need to understand the scope and approach

  • To identify potential risks and dependencies upfront

  • When coordinating work that touches multiple files

What you get:

  • Clear goal with scope boundaries

  • MVP vs nice-to-have feature breakdown

  • Step-by-step implementation guide

  • Dependency graph showing what can run in parallel

  • Risk assessment with mitigations

  • Testing strategy recommendations

  • Confidence score and clarifying questions

The plan output includes both a human-readable summary and full JSON for programmatic use. By default, plans are persisted so they can be executed later via plan_id.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskYesThe task or goal to plan for. Be specific about what you want to accomplish.
max_context_filesNoMaximum number of files to include in context analysis (default: 10)
context_token_budgetNoToken budget for context retrieval (default: 12000)
generate_diagramsNoGenerate architecture diagrams in the plan (default: true)
mvp_onlyNoFocus on MVP features only, excluding nice-to-have (default: false)
auto_saveNoPersist the generated plan for later use (default: true)
save_nameNoOptional custom name for the saved plan
save_tagsNoOptional tags for the saved plan
save_overwriteNoOverwrite existing plan with same ID when auto-saving (default: false)

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Kirachon/context-engine'

If you have feedback or need assistance with the MCP directory API, please join our Discord server