By dtannen
Comprehensive project management with AI agent coordination, task tracking, and Response Awareness methodology
Standalone complexity assessment and mode recommendation for tasks
Execute entire epic with maximum parallelization using MCP orchestration
Transform a technical epic into specific, actionable tasks with detailed implementation plans
Comprehensive guide to the PM Adaptive Workflow commands and intelligent complexity management
Initialize PM Adaptive Workflow with embedded templates and intelligent mode selection
Intelligent complexity assessment agent that analyzes tasks to determine the appropriate workflow mode for the PM Adaptive system
Lightweight RA planning review agent that validates task readiness before implementation
Specialized codebase survey agent for comprehensive domain assessment and Response_Awareness orchestration planning
You are an intelligent task execution agent that adapts its implementation approach based on complexity assessment and workflow mode configuration.
You are an intelligent verification agent that scales verification rigor based on the implementation mode and Response Awareness tags found in the codebase.
Capture hard-won insights, gotchas, and trial-and-error solutions in the knowledge system. Use when encountering non-obvious problems, multi-attempt solutions, user corrections, or debugging issues that required research.
Development patterns for PM Dashboard plugin including MCP tools, FastAPI endpoints, database operations, WebSocket broadcasting, and testing requirements. Use when working on src/task_manager/, adding features, or modifying the plugin codebase.
Response Awareness methodology for AI-assisted development with complexity scoring (1-10), assumption tagging, and knowledge capture. Use when creating tasks, managing projects, tracking assumptions, adding RA tags, or discussing complexity assessment.
Atomic task locking patterns to prevent race conditions in multi-agent environments. Use when working with task locks, concurrent operations, acquire_task_lock, update_task_status, or debugging lock conflicts.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Some configuration could not be fully parsed
Some configuration could not be fully parsed
The easiest way to get started with Claude Code:
# Add the plugin marketplace
/plugin marketplace add https://github.com/Commands-com/pm.git
# Install the plugin
/plugin install pm
# Restart Claude Code - you're ready to go!
This automatically installs:
uvx)/pm:* slash commandspip install project-manager-mcp
# or
uvx project-manager-mcp
Claude Code:
claude mcp add project-manager -- uvx project-manager-mcp
Codex:
[mcp_servers.project-manager-mcp]
command = "uvx"
args = ["project-manager-mcp"]
Gemini:
"mcpServers": {
"project-manager": {
"type": "stdio",
"command": "uvx",
"args": ["project-manager-mcp"],
"env": {}
}
}
project-manager-mcp install-claude-assets --target-dir ~/my-project
A comprehensive project management system with Model Context Protocol (MCP) support, enabling AI agents to manage projects, epics, and tasks through both programmatic interfaces and a web dashboard.
PM Dashboard includes an auto-activation system that ensures Claude actually uses skills and enforces quality standards:
Four skills automatically activate based on what you're working on:
ra-methodology - Response Awareness methodology enforcement
pm-dashboard-dev - Development patterns and architecture
src/task_manager/, adding MCP tools, writing testsknowledge-management - Capture hard-won insights
task-locking - Atomic locking patterns
Three hooks ensure quality and consistency:
UserPromptSubmit - Analyzes prompts BEFORE Claude sees them
Post-Tool-Use - Tracks file edits during work
Stop Event - Runs after Claude finishes responding
mypy, black, pytest on modified filesUser asks: "Create a task with complexity 7"
↓
UserPromptSubmit Hook matches: ra-methodology skill
↓
Injects: "🎯 Use ra-methodology skill"
↓
Claude sees prompt with skill reminder
↓
ra-methodology skill automatically loads
↓
Claude follows RA methodology patterns
↓
Stop Hook checks: RA tags added? Tests passing?
npx claudepluginhub p/commands-com-pm-claude-pluginClaude Code integration for MCP Task Orchestrator — schema-aware context, note-driven workflow
Personal work context management for AI-powered development. Track epics, issues, wiki pages, and knowledge ontology across AI agent sessions.
Commands for task management and project tracking
Fulcrum task orchestration for Claude Code
Agent Teams orchestration, governance hooks, multi-AI review, memento skill intelligence, and project management skills for Claude Code
Ultra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.