Returns information about the current project including name, status, and description

Creates a new task with title, description, status (backlog|todo|in_progress|done), dependencies, assignee, priority, and tags. ⚠️ IMPORTANT: The tool response includes automatic workflow guidance (nextSteps field) for analyzing the task before implementation. Always follow the nextSteps instructions to ensure complete metadata and dependency mapping.

Lists all tasks, optionally filtered by status and/or category

Updates an existing task. Validates status transitions and dependencies

Deletes a task. Checks for dependent tasks and prevents deletion if other tasks depend on it. Invalidates caches automatically.

Gets comprehensive context for a task including dependencies, previous work, guidelines, and tech stack

Calculates the topological execution order for tasks based on dependencies. Uses Kahn's algorithm to detect circular dependencies and return tasks sorted by execution sequence. Handles edge cases: cycles (returns error with cycle path), multiple dependency chains (ensures all paths considered), and isolated tasks (included at end).

Lists available prompt and code templates

Lists coding patterns learned from the codebase

Lists learnings from past experiences

Renders a template with provided variables

Gets relevant templates, patterns, and learnings for a task

🚀 INTELLIGENT WORKFLOW: Generates a structured prompt for Claude Code to analyze the codebase and decompose a user story based on REAL project context. Claude Code will use Grep/Glob/Read to explore the codebase before creating tasks. Returns a prompt with instructions for Claude Code to follow.

Saves the decomposition analysis performed by Claude Code after exploring the codebase. Call this after intelligent_decompose_story once you've analyzed the codebase and created the task breakdown with real file paths and dependencies.

Add feedback/learning from task execution to improve future recommendations

Find similar learnings/feedback based on context and pattern matching

Get the most frequently used patterns across all tasks, sorted by frequency and recency

Get patterns that are trending (most used in recent days), useful for identifying current development patterns

Get detailed statistics for a specific pattern including frequency, success rate, and usage timeline

Automatically detect patterns with high failure rates to identify risky approaches. Returns patterns sorted by failure rate with risk assessments and recommendations.

Check if a specific pattern has a history of failures and get risk assessment before using it. Provides immediate feedback on pattern safety.

Prepares a task for execution by generating a structured analysis request. Returns a prompt that guides Claude Code to analyze the codebase using its tools (Read, Grep, Glob). ⚠️ IMPORTANT: The response includes workflowInstructions field - follow it to know exactly what to do next. After analysis, call save_task_analysis with the results.

Saves the codebase analysis performed by Claude Code. Call this after analyzing the codebase following the prepare_task_for_execution prompt. Records dependencies, risks, and recommendations. ⚠️ IMPORTANT: The response includes nextSteps guidance - follow it to get the enriched execution prompt with all context.

Generates an enriched execution prompt with full context for implementing a task. Call this after save_task_analysis to get a comprehensive prompt with dependencies, risks, patterns, and guidelines. ⚠️ IMPORTANT: The response includes nextSteps for implementation - follow the prompt and update task status to in_progress when you start.

Save analyzed dependencies and detect potential conflicts with other tasks

Get the dependency graph (nodes and edges) for a specific task

Get all tasks that touch a specific resource

Get potential conflicts for a task based on resource usage

Get all user stories with task counts for dashboard display

Get all tasks belonging to a specific user story

Safely delete tasks by status, automatically preserving user stories with completed work and tasks with dependencies. Returns detailed report of what was deleted vs. preserved.

Get health monitoring data for all user stories, showing current vs. suggested status, completion percentage, and safety flags for deletion

Delete a user story and all its sub-tasks. Checks for completed work and external dependencies. Use force=true to delete user stories with completed sub-tasks.

Get the complete configuration for a project including tech stack, sub-agents, MCP tools, guidelines, and code patterns

Initialize default configuration for a project including tools and guardian agents

Add a technology stack entry to the project configuration

Update an existing tech stack entry

Remove a tech stack entry from the project

Add a sub-agent (guardian) to the project configuration

Update an existing sub-agent configuration

Add an MCP tool configuration to the project

Update an existing MCP tool configuration

Add a project guideline or coding standard

Add a reusable code pattern to the project library

Read and parse Claude Code agents from .claude/agents/ directory

Synchronize Claude Code agents to Orchestro database. Reads agents from .claude/agents/, parses YAML frontmatter and prompts, then upserts to sub_agents table

Get AI-powered agent suggestions for a task based on description and category. Returns top 3 most relevant agents with confidence scores

Get AI-powered MCP tool suggestions for a task based on description and category. Returns top 3 most relevant tools with confidence scores

Update prompt templates for all agent types with predefined best-practice templates

Get complete event history for a task including all status changes, decisions, code changes, and guardian interventions

Get status transition history for a task

Get all decisions made for a task

Get all guardian interventions for a task

Get all code changes for a task

Record a decision made during task execution

Record a code change made during task execution

Record a guardian intervention during task execution

Record a status transition for a task

Get the number of iterations (updates) for a task

Get a snapshot of a task at a specific point in time

Rollback a task to a previous state at a specific timestamp

Get aggregated statistics for a task including event counts and timeline