Mpm Adr logo

Mpm Adr

Community
bobmatnyc
mpm-adr

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

Overview

Publisherbobmatnyc
Repositoryclaude-mpm
Skill namempm-adr
Stars
152
Forks
34
Bundled files
Instructions only
Links
  • 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 Adr 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-adr .claude/skills/mpm-adr
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mpm Adr 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 Adr 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 Adr 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-adr

Architecture Decision Records (ADRs) are short, structured documents that capture why a significant architectural decision was made — not just what was decided. They live alongside the code so future contributors understand the constraints and trade-offs that shaped the system.

This skill is opt-in. Only use it for decisions that are architecturally significant AND costly to reverse. Over-forcing ADRs on routine work is the documented adoption-killer.


When to Write an ADR

Write an ADR only when all three conditions are true:

  1. Architecturally significant — the decision shapes how major parts of the system are structured, constrain future options, or affect multiple teams/components.
  2. Costly to reverse — undoing or changing the decision later would require substantial rework, data migration, or coordination.
  3. Not obvious from the code — the rationale is not apparent from reading the implementation alone.

Write an ADR for:

  • Choosing a database engine or persistence strategy
  • Adopting an async framework or concurrency model
  • Selecting an authentication/authorization approach
  • Defining service boundaries or API contracts
  • Committing to a major dependency or platform
  • Establishing a cross-cutting pattern (error handling, logging format)
  • Deprecating a foundational component

Do NOT write an ADR for:

  • Routine bug fixes
  • Small features or minor enhancements
  • Style/formatting decisions (use a linter config)
  • Decisions already obvious from the codebase
  • Every library version bump

If you are unsure, ask: "Would a new team member in six months need to understand why this choice was made?" If no — skip it.


File Location Convention

ScopeLocation
Workspace-wide decisionsdocs/adr/NNNN-kebab-title.md
Component-specific decisionsdocs/<component>/decisions/NNNN-kebab-title.md

Use docs/adr/ for decisions that span the whole project or affect architectural boundaries. Use docs/<component>/decisions/ for decisions scoped to a single service or library within a monorepo.


Numbering Convention

ADRs are numbered sequentially with zero-padded four-digit integers:

docs/adr/
  0000-template.md           ← master template (never a real decision)
  0001-use-postgres.md
  0002-adopt-async-framework.md
  0003-api-versioning-strategy.md

Pick the next available number by listing existing files:

bash
ls docs/adr/ | sort | tail -5

Status Lifecycle

Every ADR carries a Status field with one of these values:

StatusMeaning
ProposedDraft under discussion; not yet adopted
AcceptedAdopted — this is the current approach
DeprecatedNo longer recommended; superseded or abandoned
Superseded by [NNNN]Replaced by a later ADR (link to the new one)

When a decision changes, update the old ADR's status to Superseded by NNNN and create a new ADR for the replacement. Never delete old ADRs — the historical record is the point.


Nygard Template

markdown
# NNNN. Title (short, imperative: "Use X for Y")

Date: YYYY-MM-DD

## Status

Proposed | Accepted | Deprecated | Superseded by [NNNN](NNNN-replacement.md)

## Context

What is the issue that we are seeing that is motivating this decision?
Describe the forces at play: technical constraints, team constraints,
organizational constraints, product requirements. Be factual.

## Decision

The change that we are proposing or have agreed to implement.
State the decision clearly in active voice: "We will use X."

## Consequences

What becomes easier or more difficult as a result of this change?
List both positive and negative consequences. Include known risks.
Be honest about trade-offs — this section is the most valuable part.

Workflow

Creating a new ADR

  1. Run /mpm-init on a new project — docs/adr/ is scaffolded with README.md and 0000-template.md.
  2. Copy 0000-template.md to NNNN-your-title.md with the next number.
  3. Fill in Context, Decision, and Consequences. Set Status to Proposed.
  4. Submit for review. Once agreed, change Status to Accepted.
  5. Commit with: docs: ADR-NNNN adopt X for Y

Superseding an ADR

  1. Create a new ADR (MMMM-new-approach.md) with Status Accepted.
  2. Edit the old ADR's Status to Superseded by [MMMM](MMMM-new-approach.md).
  3. Commit both files together.

Follow-up (Stretch Goal)

A future documentation-agent hook could auto-draft ADRs from significant commits or conversation context. This is tracked as a follow-up to issue #562 and is not part of the current implementation.


References

  • Michael Nygard, "Documenting Architecture Decisions" (2011)
  • bobmatnyc/trusty-tools — prior art for this convention
  • docs/features/adr.md — trigger criteria and hybrid location guide

Frequently asked questions

What does the Mpm Adr AI skill do?

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

Why use Mpm Adr on TypingMind?

Because you install it once and use it with any model. Mpm Adr 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 Adr in TypingMind?

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

Which AI models can use Mpm Adr?

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 Adr?

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

Is the Mpm Adr 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

Set up your own AI workspace now

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