Skip to main content
Glama

plan_task

Creates structured plans for coding tasks by breaking work into steps with dependencies, validation criteria, and complexity estimates. Use before starting significant coding work.

Instructions

Creates a structured plan for completing a coding task. Breaks down the work into steps with dependencies, validation criteria, and estimated complexity. Use before starting any significant coding work.

Input Schema

NameRequiredDescriptionDefault
taskYesDescription of the task to plan
contextNoCurrent project context, tech stack, constraints
scopeNoExpected scope of the task

Input Schema (JSON Schema)

{ "$schema": "http://json-schema.org/draft-07/schema#", "additionalProperties": false, "properties": { "context": { "description": "Current project context, tech stack, constraints", "type": "string" }, "scope": { "description": "Expected scope of the task", "enum": [ "small", "medium", "large" ], "type": "string" }, "task": { "description": "Description of the task to plan", "type": "string" } }, "required": [ "task" ], "type": "object" }

Implementation Reference

  • The main handler function for the 'plan_task' tool. It generates a structured markdown plan based on the input task, optional context, and scope. Returns a text content block with the plan.
    export function planTaskHandler(args: any) { const { task, context = "", scope = "medium" } = args; const plan = `# Task Plan: ${task} ## Context ${context || "No additional context provided."} ## Scope Assessment **Estimated Scope**: ${scope} ## Pre-Implementation Checklist - [ ] Understand requirements fully - [ ] Identify affected files/components - [ ] Consider edge cases - [ ] Plan for testing ## Implementation Steps ### Step 1: Analysis - Review existing codebase - Identify integration points - Document assumptions ### Step 2: Design - Define interfaces/types - Plan component structure - Consider error handling ### Step 3: Implementation - Write core functionality - Follow coding standards - Add inline documentation ### Step 4: Testing - Write unit tests - Test edge cases - Integration testing ### Step 5: Review - Self-review code - Check for security issues - Validate performance ## Validation Criteria - [ ] All tests pass - [ ] No linting errors - [ ] Documentation updated - [ ] Code reviewed ## Rollback Plan If issues arise, revert to previous state and reassess approach. `; return { content: [{ type: "text", text: plan }] }; }
  • The Zod schema definition for the 'plan_task' tool, defining input parameters: task (required string), context (optional string), scope (optional enum).
    export const planTaskSchema = { name: "plan_task", description: "Creates a structured plan for completing a coding task. Breaks down the work into steps with dependencies, validation criteria, and estimated complexity. Use before starting any significant coding work.", inputSchema: z.object({ task: z.string().describe("Description of the task to plan"), context: z.string().optional().describe("Current project context, tech stack, constraints"), scope: z.enum(["small", "medium", "large"]).optional().describe("Expected scope of the task") }) };
  • src/server.ts:89-89 (registration)
    Registration of the 'plan_task' tool in the toolRegistry Map used by the HTTP server in src/server.ts.
    ["plan_task", { schema: planTaskSchema, handler: planTaskHandler }],
  • src/index.ts:79-79 (registration)
    Registration of the 'plan_task' tool in the toolRegistry Map used by the stdio MCP server in src/index.ts.
    ["plan_task", { schema: planTaskSchema, handler: planTaskHandler }],

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/millsydotdev/Code-MCP'

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