Mpm Agent Update Workflow logo

Mpm Agent Update Workflow

Community
bobmatnyc
mpm-agent-update-workflow

Workflow for updating, fixing, and improving MPM agents

Overview

Publisherbobmatnyc
Repositoryclaude-mpm
Skill namempm-agent-update-workflow
Stars
152
Forks
34
Bundled files
Instructions only
Links
Skill sourceRepository
  • 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 Agent Update Workflow AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. 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.
2

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-agent-update-workflow .claude/skills/mpm-agent-update-workflow
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mpm Agent Update Workflow 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 Agent Update Workflow 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 Agent Update Workflow 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.

PM Skill: Agent Update Workflow

Trigger Patterns

  • "update agent", "fix agent", "improve agent", "modify agent"
  • "change {agent-name} agent", "edit agent instructions"
  • Any request to modify agent behavior

FUNDAMENTAL RULE: Official vs Custom Agents

Official MPM Agents (NEVER edit deployed copies)

Source: ~/.claude-mpm/cache/agents/ (from bobmatnyc/claude-mpm-agents repo) Deployed: .claude/agents/ - READ-ONLY for official agents

Detection: Check if agent exists in ~/.claude-mpm/cache/agents/

  • If YES → Official agent → Follow Official Agent Workflow
  • If NO → Custom agent → Can edit .claude/agents/ directly

Custom/Localized Agents

  • Created specifically for project
  • Can be edited directly in .claude/agents/
  • Not part of official MPM agent set

Official Agent Update Workflow

Step 1: Identify Agent Source

bash
ls ~/.claude-mpm/cache/agents/  # Find the source file

Step 2: Update Source

Edit the agent source in ~/.claude-mpm/cache/agents/{agent-name}.md (or appropriate path based on agent structure)

Step 3: Rebuild and Redeploy

Use MPM deployment tools:

bash
# Redeploy specific agent
mpm agents deploy {agent-name}

# Or redeploy all agents
mpm agents deploy --all

Step 4: Validate (claude-mpm project only)

When working in the claude-mpm project itself:

bash
# Run deepeval against deployed agent instructions
deepeval test --agent {agent-name}

Circuit Breaker

BLOCK if attempting to edit .claude/agents/{official-agent}.md directly:

  • Official agents in deployed location are BUILD OUTPUTS
  • Must update source → rebuild → redeploy
  • Violation = architectural breach

Examples

❌ WRONG (Editing deployed official agent)

Edit: .claude/agents/web-qa.md  # VIOLATION - this is a built output

✅ CORRECT (Updating source and redeploying)

1. Edit: ~/.claude-mpm/cache/agents/web-qa.md  # Update source
2. Run: mpm agents deploy web-qa                # Rebuild/redeploy
3. Validate: deepeval test --agent web-qa       # (in claude-mpm project)

✅ CORRECT (Custom agent - can edit directly)

Edit: .claude/agents/my-custom-agent.md  # OK - not an official agent

Frequently asked questions

What does the Mpm Agent Update Workflow AI skill do?

Workflow for updating, fixing, and improving MPM agents

Why use Mpm Agent Update Workflow on TypingMind?

Because you install it once and use it with any model. Mpm Agent Update Workflow 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 Agent Update Workflow in TypingMind?

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

Which AI models can use Mpm Agent Update Workflow?

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 Agent Update Workflow?

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

Is the Mpm Agent Update Workflow 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.

Related AI Skills

View all
vercel logo

Next Partial Prefetching Optimizer

vercel
OrganizationPopular

Optimize what selected Next.js client navigations include before the click under Partial Prefetching. Use after Cache Components and Partial Prefetching are adopted when the user wants selected…

32.4K
142.3K
2 files
View
DietrichGebert logo

Ponytail Gain

DietrichGebert
CommunityPopular

Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger:…

7.6K
141.3K
Instructions
View
garrytan logo

Benchmark Models

garrytan
CommunityPopular

Cross-model benchmark for gstack skills. (gstack)

19.9K
133.5K
1 files
View
garrytan logo

Benchmark

garrytan
CommunityPopular

Performance regression detection. (gstack)

19.9K
133.5K
1 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇