claude-mpm

MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Claude Desktop integration.

Model Context Protocol (MCP) server build and evaluation guide, including local conventions for tool surfaces, config, and testing

Control monitoring server and dashboard

Pause session and save current work state for later resume

Load context from paused session

Access Claude MPM functionality and manage multi-agent orchestration

Control monitoring server and dashboard

Pause session and save current work state for later resume

Load context from paused session

Access Claude MPM functionality and manage multi-agent orchestration

Manage and customize MPM workflow configurations with local overrides

Branch protection and PR creation workflow

Drive the trusty-mpm session manager (binary `tm`) to spawn, observe, command, and decommission durable tmux-backed Claude Code sessions in isolated workspaces. Wraps the `tm session` CLI / REST API and provides the spawn → observe → answer → stop/resume/decommission loop. Critically, the DRIVER interprets the raw tmux pane using its own inference — it does NOT depend on the daemon's optional LLM (no OpenRouter key required).

Rust 2024 edition core patterns: idiomatic code, error handling, traits/generics, macros, async/concurrency, testing, and project architecture

Spec-Linked Documentation (SLD): Language-agnostic discipline for maintaining bidirectional traceability between functional specifications and source-code docstrings via stable identifiers and CI validation. Optional/opt-in adoption. Builds on OpenFastTrace and DO-178C Requirements Traceability Matrix traditions.

Debug and teach agentic coding: a deterministic-first session timeline + cost report, with optional narrative polish and a standalone JSX visualiser.

Go 1.22-1.24 core patterns for minimalism, efficiency, code reuse, and performance

Dispatch code-reviewer subagent to review implementation against plan or requirements before proceeding

Methodical debugging instead of random changes

Security review gate for MCP server installations. Checks provenance, classifies risk, enforces version pinning, and documents credentials exposure before any MCP is added to your environment.

Branch protection and PR creation workflow

Bug reporting protocol for PM and agents to file GitHub issues

Protocol for tracking files immediately after agent creation

Bug reporting protocol for PM and agents to file GitHub issues

Protocol for tracking files immediately after agent creation

Standard for authoring product PRDs in docs/prd/: state the problem, users, requirements, and success; assign PRD-{AREA}-{NN} IDs; link down to specs.

Standard for authoring engineering behavior-contract specs in docs/specs/: scope subsystems, assign stable IDs, structure docs, manage lifecycle.

Complete circuit breaker enforcement patterns with examples and remediation

Use multiple Claude agents to investigate and fix independent problems concurrently

Architecture Decision Records (ADRs) — opt-in convention for documenting significant, hard-to-reverse architectural decisions using the Nygard template.

Orchestrate ticketing agent for project management workflows

Ticket-driven development protocol

Orchestrate ticketing agent for project management workflows

Ticket-driven development protocol

Complete circuit breaker enforcement patterns with examples and remediation

Catalog and router for migration skill wizards (service installation guides)

Install and configure trusty-memory and trusty-search for persistent AI memory and semantic code search

General protocol for executing migration skill wizards - service installation and configuration guides

Persistent memory palace system with hierarchical storage (palace/wing/room/closet/drawer), progressive retrieval (L0-L3), and temporal knowledge graph for cross-session context

Hybrid code search (BM25 + vector + KG) with RRF fusion. Single daemon serves multiple named indexes. Replaces mcp-vector-search.