MCAF is a framework for building software products together with AI coding agents.

MCAF Concepts

Managed Code Coding AI Framework

Developed and sustained by Managed Code
March 2026

1. What MCAF Is

MCAF is a framework for building real software with AI coding agents.

It defines how to:

• keep durable engineering context in the repository
• make AI work from AGENTS.md plus repo-native docs and skills
• verify behaviour with tests and static analysis
• keep AI guidance small, explicit, and versioned

The goal of MCAF:

Use AI to build real products in a way that is predictable, safe, and repeatable.

MCAF has three core elements:

• Context — code, docs, AGENTS.md, and skills live with the repo.
• Verification — tests and analyzers are the decision makers, not opinions.
• Instructions — root and local AGENTS.md files define how agents work here.

These concepts define the framework (the "what" and "why").
TUTORIAL.md is the bootstrap procedure (the "how").
Repository AGENTS.md files apply both to a specific solution.

1.1 Bootstrap Surface

v1.2 is skill-first.

Bootstrap stays minimal:

• one root AGENTS.md template
• one CLAUDE.md wrapper template
• one tutorial page that explains how agents fetch and install the right skill folders

Canonical install entry point:

• Tutorial: https://mcaf.managed-code.com/tutorial

Optional direct shortcuts:

• Templates: https://mcaf.managed-code.com/templates
• Skills: https://mcaf.managed-code.com/skills

2. Context

Context is everything needed to understand, change, and run the system.

2.1 Repository Context

In MCAF, repository context includes:

• application code
• automated tests
• architecture, feature, ADR, and operational docs
• skills for repeatable agent workflows
• the solution-root AGENTS.md
• project-local AGENTS.md files for multi-project solutions

Anything that materially affects development, veri