adr-review

Coordinate six agents to review Architecture Decision Records and produce MADR 4.0 compliant updates.

Updated Jan 19, 2026

Search Tags:#multi-agent #governance #consensus #debate #MADR #architecture-decision #adr-review

Ready to run

npx skills add https://github.com/loriensleafs/brain --skill adr-review-loriensleafs

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: adr-review
Source: https://github.com/loriensleafs/brain/tree/main/apps/claude-plugin/skills/adr-review
Command: npx skills add https://github.com/loriensleafs/brain --skill adr-review-loriensleafs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill orchestrates a six-agent review process for Architecture Decision Records (ADRs), automating governance workflows and ensuring rigorous validation before decisions are accepted.

Core Features & Use Cases

Multi-agent debate orchestration: architect, critic, independent-thinker, security, analyst, and high-level-advisor collaborate through structured review rounds.
Automatic ADR change detection: triggers reviews on ADR creation, updates, or deletions to maintain governance integrity.
MADR 4.0 aligned outputs: produces debate logs and updated ADR texts with clear accountability and traceability.

Quick Start

Use the adr-review skill to validate an ADR:

Manual trigger: adr-review .agents/architecture/ADR-005-api-versioning.md
Manual prompts: "review this ADR" and "validate ADR"
Automatic detection: Detect-ADRChanges.ps1 runs at session start to prompt ADR review.

Frequently Asked Questions about adr-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate architecture decision record reviews for governance?▼

Multi-agent debate validates ADRs by orchestrating six specialized agents—architect, critic, independent-thinker, security, analyst, and high-level-advisor—through structured review rounds to drive consensus.

Can I use multi-agent consensus to validate MADR 4.0 compliant files?▼

Yes, multi-agent consensus validates MADR 4.0 files by producing updated ADR texts and debate logs with clear accountability, ensuring architecture decisions meet rigorous governance standards.

How do I trigger an ADR review automatically when files change?▼

Trigger ADR reviews automatically via Detect-ADRChanges.ps1 at session start, or manually by passing the ADR file path to validate architecture decisions.

What is the best way to structure a debate around architecture decisions?▼

Structure architecture decision debates using a multi-agent approach where specialized roles—architect, critic, security, and analyst—collaborate through review rounds to produce traceable governance logs.

Does ADR governance work without dependencies?▼

Yes, this ADR governance workflow operates without external dependencies, relying solely on its internal scripts and references to orchestrate multi-agent reviews.

When should I not use a multi-agent approach for ADR validation?▼

Avoid multi-agent ADR validation for simple, low-impact decisions where the overhead of a six-agent debate outweighs the need for rigorous governance consensus.