# Project Task Manager ## Links - Product page URL: https://www.agentpmt.com/marketplace/project-task-manager - Product markdown URL: https://www.agentpmt.com/marketplace/project-task-manager?format=agent-md - Product JSON URL: https://www.agentpmt.com/marketplace/project-task-manager?format=agent-json ## Overview - Product ID: 694f3f25119f659009bc8692 - Vendor: Apoth3osis - Type: function - Unit type: request - Price: 2000 credits - Categories: Developer Tools, Testing & QA, Task Planning & Orchestration, Project Management, Sorting & Ordering - Generated at: 2026-05-30T20:16:10.751Z ### Page Description AI Powered task generation and project management service that transforms high-level objectives into structured, hierarchical task breakdowns using large language model reasoning. The generate action accepts a project goal or objective along with optional context about available technologies and constraints, then produces a complete task tree with priorities, time estimates, dependencies between tasks, recommended tools, and measurable success criteria. The AI automatically selects the optimal prompting strategy based on objective complexity, using Chain of Thought reasoning for complex goals, ReAct methodology for technical implementations, or direct generation for straightforward requests. Task hierarchies can be configured from 1 to 4 levels deep depending on desired granularity. The decompose action breaks individual tasks into smaller actionable steps at basic, standard, or detailed levels without creating a persistent tree. Progress tracking supports updating task status through pending, in progress, completed, failed, and blocked states with percentage completion and notes. The status action provides real-time progress summaries including completed task counts, currently active work, blocked items, and estimated completion times. All generated task trees persist across sessions with full history available through the list action, enabling long-running project tracking and multi-session workflows. ### Agent Description AI-powered task planning: generate hierarchical task trees from objectives, decompose tasks, track progress, visualize status. Persistent across sessions. ## Details ### Details AI Powered task generation and project management service that transforms high-level objectives into structured, hierarchical task breakdowns using large language model reasoning. The generate action accepts a project goal or objective along with optional context about available technologies and constraints, then produces a complete task tree with priorities, time estimates, dependencies between tasks, recommended tools, and measurable success criteria. The AI automatically selects the optimal prompting strategy based on objective complexity, using Chain of Thought reasoning for complex goals, ReAct methodology for technical implementations, or direct generation for straightforward requests. Task hierarchies can be configured from 1 to 4 levels deep depending on desired granularity. The decompose action breaks individual tasks into smaller actionable steps at basic, standard, or detailed levels without creating a persistent tree. Progress tracking supports updating task status through pending, in progress, completed, failed, and blocked states with percentage completion and notes. The status action provides real-time progress summaries including completed task counts, currently active work, blocked items, and estimated completion times. All generated task trees persist across sessions with full history available through the list action, enabling long-running project tracking and multi-session workflows. ### Actions - `generate` (20 credits): Create a hierarchical task breakdown from a high-level objective. An AI model analyzes the objective and produces a structured tree of tasks with dependencies, time estimates, and priorities. - `update` (20 credits): Mark progress on a specific task within a task tree. Update status, completion percentage, and add notes about what happened. - `decompose` (20 credits): Break a single task description into smaller, actionable subtasks. Standalone operation that does not require an existing task tree. - `status` (20 credits): Check the current progress and status of a task tree. Returns overall progress, completed/remaining tasks, blocked items, and estimated completion time. - `list` (20 credits): Show all your task trees sorted by most recently updated. Returns up to 50 trees with their IDs, objectives, task counts, and progress. ### Use Cases AI task generation, automatic task breakdown, project decomposition, objective to tasks, goal decomposition, hierarchical task creation, work breakdown structure, WBS generation, project planning automation, sprint planning, task prioritization, dependency mapping, task dependency graph, time estimation, effort estimation, project scoping, technical project planning, software development planning, API development tasks, feature breakdown, epic decomposition, user story generation, milestone planning, roadmap generation, task tree creation, subtask generation, action item creation, project management automation, agile planning, task tracking, progress monitoring, project status tracking, completion tracking, blocked task identification, task status updates, progress percentage tracking, task notes, work logging, project timeline estimation, remaining work calculation, estimated completion time, multi-level task hierarchy, LLM task planning, AI project manager, automated planning, workflow generation, implementation planning, development task breakdown, technical decomposition, Chain of Thought planning, ReAct task generation, AI agent task management, autonomous agent planning, long-running project tracking ### Workflows Using This Tool No public workflows currently reference this product. ### Related Content No related content is currently linked to this product. ## Integration Details ### DynamicMCP - Setup page URL: https://www.agentpmt.com/dynamic-mcp - Claude setup guide: https://www.agentpmt.com/dynamic-mcp?platform=claude#videos - ChatGPT setup guide: https://www.agentpmt.com/dynamic-mcp?platform=chatgpt#videos - Cursor setup guide: https://www.agentpmt.com/dynamic-mcp?platform=cursor#videos - Windsurf setup guide: https://www.agentpmt.com/dynamic-mcp?platform=windsurf#videos Use the local router for command-based MCP clients. It forwards requests to `https://api.agentpmt.com/mcp` and does not execute tools locally. ```bash npm install -g @agentpmt/mcp-router agentpmt-setup ``` ### REST API The live page renders cURL, Python, JavaScript, and Node.js examples. Logged-in users see those examples prefilled with their own API and budget credentials. - Purchase endpoint: https://api.agentpmt.com/products/purchase - Authorization format: `Bearer ` ```bash curl -X POST "https://api.agentpmt.com/products/purchase" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer eW91ci1hcGkta2V5LWhlcmU6eW91ci1idWRnZXQta2V5LWhlcmU=" \ -d '{ "product_id": "694f3f25119f659009bc8692", "parameters": { "action": "generate", "objective": "example_objective" } }' ``` ### Autonomous Agents Autonomous agents can access this tool through AgentAddress credit balances or direct x402 payments. Use the Autonomous Agent API reference for endpoint shapes after choosing the access pattern below. - Autonomous Agent API reference URL: https://www.agentpmt.com/docs/api-reference/autonomous-agents - Autonomous Agent API reference markdown URL: https://www.agentpmt.com/docs/api-reference/autonomous-agents?format=agent-md - Credit-Based Access Using AgentAddress: https://www.agentpmt.com/docs/autonomous-agents/credit-based-tool-usage-with-agentaddress - AgentAddress is preferred for persistent file access, stored platform state, and maximum tool use ability across repeated calls. - Direct x402 is for independent one-off tool calls that do not require shared files or stored platform state. - Direct x402 public payments: USDC on Base, Arbitrum, Optimism, Polygon, and Avalanche. ### Schema #### Parameters - Schema type: actions ```json { "actions": { "generate": { "description": "Create a hierarchical task breakdown from a high-level objective. An AI model analyzes the objective and produces a structured tree of tasks with dependencies, time estimates, and priorities.", "properties": { "objective": { "type": "string", "description": "What you want to accomplish. Be specific about the end goal. Max 2000 characters. Example: 'Build a REST API for user management with JWT authentication'.", "required": true }, "context": { "type": "object", "description": "Technologies or constraints. Example: {\"tech\": [\"python\", \"postgresql\"], \"constraints\": [\"must use docker\", \"deploy to AWS\"]}.", "properties": {}, "required": false }, "max_depth": { "type": "integer", "description": "How many levels deep to break down tasks. 2 = simple, 3 = standard (default), 4 = very detailed.", "required": false } } }, "update": { "description": "Mark progress on a specific task within a task tree. Update status, completion percentage, and add notes about what happened.", "properties": { "tree_id": { "type": "string", "description": "The tree_id returned from the generate action. Identifies which project you are working on.", "required": true }, "task_id": { "type": "string", "description": "The specific task_id to update. Use one of the task_ids from the generate response.", "required": true }, "task_status": { "type": "string", "description": "New status for the task. Use 'in_progress' when you start, 'completed' when done, 'failed' if you cannot do it, 'blocked' if you are stuck.", "enum": [ "pending", "in_progress", "completed", "failed", "blocked" ], "required": false }, "progress": { "type": "number", "description": "How complete is this task. 0 = not started, 50 = halfway done, 100 = finished.", "required": false }, "notes": { "type": "string", "description": "What you learned or what happened while working on this task. Keep it brief. Max 500 characters.", "required": false } } }, "decompose": { "description": "Break a single task description into smaller, actionable subtasks. Standalone operation that does not require an existing task tree.", "properties": { "task": { "type": "string", "description": "The task to break into smaller steps. Be specific. Example: 'Implement user login with session management'.", "required": true }, "level_of_detail": { "type": "string", "description": "How detailed the breakdown should be. 'basic' (3-5 steps), 'standard' (5-10 steps, default), 'detailed' (10-15 steps).", "enum": [ "basic", "standard", "detailed" ], "required": false } } }, "status": { "description": "Check the current progress and status of a task tree. Returns overall progress, completed/remaining tasks, blocked items, and estimated completion time.", "properties": { "tree_id": { "type": "string", "description": "The tree_id returned from the generate action.", "required": true } } }, "list": { "description": "Show all your task trees sorted by most recently updated. Returns up to 50 trees with their IDs, objectives, task counts, and progress." } }, "properties": { "action": { "type": "string", "description": "Use 'get_instructions' to retrieve documentation. REQUIRED. What to do: 'generate' (create task breakdown), 'update' (mark progress), 'decompose' (break down one task), 'status' (check progress), 'list' (show all trees)", "required": true, "enum": [ "get_instructions", "generate", "update", "decompose", "status", "list" ] }, "objective": { "type": "string", "description": "[generate action] What you want to accomplish. Be specific about the end goal. Example: 'Build a REST API for user management with JWT authentication'", "required": false }, "context": { "type": "object", "description": "[generate action] OPTIONAL. Technologies you're using or constraints you have. Example: {\"tech\": [\"python\", \"postgresql\"], \"constraints\": [\"must use docker\", \"deploy to AWS\"]}", "required": false }, "max_depth": { "type": "integer", "description": "[generate action] OPTIONAL. How many levels deep to break down tasks. 2 = simple breakdown, 3 = standard (default), 4 = very detailed", "required": false, "default": 3, "minimum": 1, "maximum": 4 }, "tree_id": { "type": "string", "description": "[update/status actions] REQUIRED. The tree_id you got back from the generate action. This identifies which project you're working on.", "required": false }, "task_id": { "type": "string", "description": "[update action] REQUIRED. Which specific task to update. Use one of the task_ids from the generate response.", "required": false }, "status": { "type": "string", "description": "[update action] New status for the task. Use 'in_progress' when you start, 'completed' when done, 'failed' if you can't do it, 'blocked' if you're stuck.", "required": false, "enum": [ "pending", "in_progress", "completed", "failed", "blocked" ] }, "progress": { "type": "number", "description": "[update action] OPTIONAL. How complete is this task? 0 = not started, 50 = halfway done, 100 = finished. Useful for partial progress.", "required": false, "minimum": 0, "maximum": 100 }, "notes": { "type": "string", "description": "[update action] OPTIONAL. What you learned or what happened while working on this task. Keep it brief.", "required": false }, "task": { "type": "string", "description": "[decompose action] REQUIRED. The task you want to break into smaller steps. Be specific. Example: 'Implement user login with session management'", "required": false }, "level_of_detail": { "type": "string", "description": "[decompose action] OPTIONAL. How detailed the breakdown should be: 'basic' (3-5 steps), 'standard' (5-10 steps, default), 'detailed' (10-15 steps)", "required": false, "default": "standard", "enum": [ "basic", "standard", "detailed" ] } } } ``` ### Usage Instructions # Project Task Manager AI-powered task generation and project management tool. Break down objectives into structured, hierarchical task trees with dependencies, priorities, and time estimates. Track progress as you work through tasks. ## Actions ### generate Create a hierarchical task breakdown from a high-level objective. An AI model analyzes your objective and produces a structured tree of tasks with dependencies, time estimates, and priorities. **Required fields:** - `action`: `"generate"` - `objective` (string): What you want to accomplish. Be specific about the end goal. Max 2000 characters. **Optional fields:** - `context` (object): Technologies or constraints. Example: `{"tech": ["python", "postgresql"], "constraints": ["must use docker", "deploy to AWS"]}` - `max_depth` (integer, 1-4): How many levels deep to break down tasks. 2 = simple, 3 = standard (default), 4 = very detailed. **Example:** ```json { "action": "generate", "objective": "Build a REST API for user management with JWT authentication", "context": {"tech": ["python", "fastapi"], "constraints": ["must use PostgreSQL"]}, "max_depth": 3 } ``` **Response includes:** `tree_id` (save this for future actions), `task_ids` (list of all task IDs), `tasks` (full hierarchy), `total_tasks`, `estimated_total_time` (minutes), and `dependency_graph`. --- ### update Mark progress on a specific task within a task tree. Use this as you start, complete, or get blocked on tasks. **Required fields:** - `action`: `"update"` - `tree_id` (string): The tree_id returned from the generate action. - `task_id` (string): The specific task_id to update (from the generate response task_ids list). **At least one of these is required:** - `status` (string): New status. One of: `"pending"`, `"in_progress"`, `"completed"`, `"failed"`, `"blocked"`. - `progress` (number, 0-100): Completion percentage. 0 = not started, 50 = halfway, 100 = done. - `notes` (string): What happened or what you discovered. Max 500 characters. **Example:** ```json { "action": "update", "tree_id": "abc-123-def", "task_id": "task-456", "status": "in_progress", "progress": 25, "notes": "Started implementing the database schema" } ``` **Response includes:** `updates_applied`, `new_progress` (overall tree progress), and `tasks_remaining`. --- ### decompose Break a single task description into smaller, actionable subtasks. This is a standalone operation that does not require an existing task tree. **Required fields:** - `action`: `"decompose"` - `task` (string): The task to break into smaller steps. Be specific. **Optional fields:** - `level_of_detail` (string): How detailed the breakdown should be. One of: `"basic"` (3-5 steps), `"standard"` (5-10 steps, default), `"detailed"` (10-15 steps). **Example:** ```json { "action": "decompose", "task": "Implement user login with session management and password reset", "level_of_detail": "detailed" } ``` **Response includes:** `subtasks` (list with name, description, estimated_time, dependencies, and tools for each), `total_subtasks`. --- ### status Check the current progress and status of a task tree. **Required fields:** - `action`: `"status"` - `tree_id` (string): The tree_id returned from the generate action. **Example:** ```json { "action": "status", "tree_id": "abc-123-def" } ``` **Response includes:** `overall_progress` (percentage), `completed_tasks`, `total_tasks`, `current_tasks` (in-progress tasks), `blocked_tasks`, `estimated_completion`, and `last_updated`. --- ### list Show all your task trees, sorted by most recently updated. Returns up to 50 trees. **Required fields:** - `action`: `"list"` **Example:** ```json { "action": "list" } ``` **Response includes:** `trees` (list with tree_id, objective, task_count, progress, created_at, updated_at for each), `total`. --- ## Common Workflows ### Plan and Execute a Project 1. Use `generate` with your objective to create a task tree. Save the returned `tree_id` and `task_ids`. 2. Use `status` with the `tree_id` to review the plan. 3. Use `update` to mark tasks as `"in_progress"` when you start them. 4. Use `update` to mark tasks as `"completed"` when finished, or `"blocked"` / `"failed"` if issues arise. 5. Use `status` periodically to check overall progress. ### Quick Task Breakdown Use `decompose` when you just need to break a single task into steps without creating a full project tree. Good for ad-hoc planning. ### Resume Previous Work Use `list` to find your existing task trees, then `status` with the relevant `tree_id` to see where you left off. ## Important Notes - The `tree_id` returned from `generate` is required for all `update` and `status` calls. Always save it. - Task IDs come from the `task_ids` array in the generate response. Use these exact IDs when calling `update`. - Setting status to `"completed"` automatically sets progress to 100%. - Time estimates are in minutes. - The `decompose` action is independent and does not create or modify task trees. - Task trees are stored per user and persist between sessions. ### Frequently Asked Questions #### How do I connect this tool to an external agent? - Page URL: https://www.agentpmt.com/faq - Markdown URL: https://www.agentpmt.com/faq?format=agent-md You can install the local MCP server by opening a terminal and running: ``` npm install -g @agentpmt/mcp-router agentpmt-setup ``` This will connect you to local agents like Claude Code, Windsurf, Grok Build, Cursor, etc. Alternatively you can connect to the hosted version with this config block, no installation required: ``` { "mcpServers": { "agentpmt": { "type": "streamable-http", "url": "https://api.agentpmt.com/mcp", "headers": { "Authorization": "Bearer ", "x-instance-metadata": "{\"client\":\"generic-mcp\",\"platform\":\"remote\"}" } } } } ``` [View MCP Connection Instructions](/docs/mcp-reference/connection) for more details. #### How does an external agent use this tool? - Page URL: https://www.agentpmt.com/faq - Markdown URL: https://www.agentpmt.com/faq?format=agent-md After the external agent is connected to an Agent Group that can use this tool, paste this prompt into the agent: > Call the AgentPMT-Tool-Search-and-Execution tool with action 'get\_schema' and tool\_id 694f3f25119f659009bc8692 ("Project Task Manager"). Then call the same tool with action 'call\_tool', tool\_id 694f3f25119f659009bc8692, and the parameters needed for my request. The agent should fetch the tool schema first, collect the required parameters for your request, and then call the tool through AgentPMT. ### Dependencies This product has no public dependency products.