Mpm Init

Community

bobmatnyc

mpm-init

Initialize or update project for Claude Code and MPM

Overview

Publisher	bobmatnyc
Repository	`claude-mpm`
Skill name	`mpm-init`
Stars	152
Forks	34
Bundled files	Instructions only
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by bobmatnyc on GitHub. Read the source before you install it.

Installation

Install the Mpm Init AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/bobmatnyc/claude-mpm.git /tmp/claude-mpm
mkdir -p .claude/skills
cp -r /tmp/claude-mpm/plugin/skills/mpm-init .claude/skills/mpm-init

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mpm Init in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mpm Init on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mpm Init is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

/mpm-init

Initialize or intelligently update project for Claude Code and Claude MPM.

Usage


/mpm-init [update|context|resume|catchup] [options]

Core Modes

Project Setup


/mpm-init                      # Auto-detect: offer update or create
/mpm-init update               # Quick update (30-day git activity)
/mpm-init --update             # Full documentation refresh
/mpm-init --force              # Force recreate from scratch

Delegates to Agentic Coder Optimizer agent for:

CLAUDE.md creation/update (with priority rankings 🔴🟡🟢⚪)
AST analysis and code structure docs
Single-path workflows (ONE way to do ANYTHING)
Tool configuration, memory system, gitignore management

Smart Update Mode: Auto-detects existing CLAUDE.md and offers update vs recreate.

Context Analysis


/mpm-init context [--days N]   # Intelligent git history analysis (default: 7 days)
/mpm-init catchup              # Quick commit history (last 25 commits, no analysis)

context: Delegates to Research agent for deep analysis of:

Active work streams (from commit patterns)
Intent and motivation (from messages)
Risks and blockers
Recommended next actions

catchup: Direct CLI execution, instant output.

Resume from Logs


/mpm-init resume [--list] [--session-id ID]

Reads stop event logs from .claude-mpm/resume-logs/ and .claude-mpm/responses/ showing:

What was being worked on
Tasks completed, files modified
Next steps, stop reason, token usage
Git context (branch, status)

Key Options

Configuration:

--project-type TYPE: web, api, cli, library
--framework NAME: react, django, fastapi, etc.
--ast-analysis / --no-ast-analysis: Enable/disable code analysis
--comprehensive / --minimal: Full setup vs CLAUDE.md only

Organization:

--organize: Organize misplaced files
--preserve-custom: Keep custom sections (default)
--review: Review without changes

What Gets Created

New Projects:

✅ CLAUDE.md (priority-ranked instructions)
✅ Single-path workflows (make build/test/deploy)
✅ Tool configs (linting, formatting, testing)
✅ Memory system (.claude-mpm/memories/)
✅ DEVELOPER.md, CODE_STRUCTURE.md (with AST)
✅ .gitignore updates (auto-adds .claude-mpm/)

Updates:

✅ Smart merging (preserves custom sections)
✅ Automatic archival (docs/_archive/)
✅ Change tracking

Examples

bash
# Quick start
/mpm-init                      # Auto-detect mode

# Quick update (lightweight)
/mpm-init update               # 30-day activity report

# Resume work
/mpm-init context --days 14    # Analyze last 2 weeks
/mpm-init resume               # Show latest session from logs
/mpm-init catchup              # Quick commit history

# Full configuration
/mpm-init --project-type web --framework react --comprehensive

Implementation Notes

Delegation patterns:

Project init/update: → Agentic Coder Optimizer agent
context: → PM → Research agent (structured analysis)
catchup: → Direct CLI (git log wrapper)
resume: → PM (reads logs, no delegation)

Token budgets:

context analysis: 10-30s processing time
resume display: ~10-20k tokens
catchup: instant, minimal tokens

See docs/commands/init.md for comprehensive documentation.

Frequently asked questions

What does the Mpm Init AI skill do?

Initialize or update project for Claude Code and MPM

Why use Mpm Init on TypingMind?

Because you install it once and use it with any model. Mpm Init is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mpm Init in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bobmatnyc/claude-mpm/tree/main/plugin/skills/mpm-init. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Mpm Init?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mpm Init?

As many as you like. As long as a model supports skills, you can use Mpm Init with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mpm Init AI skill free?

It is published on GitHub by bobmatnyc. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Requesting Code Review

obra

CommunityPopular

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Systematic Debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Test Driven Development

obra

CommunityPopular

Use when implementing any feature or bugfix, before writing implementation code

Using Git Worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

/mpm-init

Usage

Core Modes

Project Setup

Context Analysis

Resume from Logs

Key Options

What Gets Created

Examples

Implementation Notes

Frequently asked questions

Related AI Skills

Set up your own AI workspace now