adr

Update an existing ADR (status, content, or metadata)

Export ADRs to HTML, JSON, or PDF format

List all ADRs with optional status filtering

Create a new Architectural Decision Record

Search ADRs by content, status, tags, or date

Use this agent proactively when architectural decisions are being discussed in conversation. This agent detects keywords and patterns indicating architectural discussions and suggests capturing decisions as ADRs. Examples: <example> Context: User is discussing which database to use for a new feature. user: "Should we use PostgreSQL or MongoDB for the new analytics data?" assistant: "I notice you're discussing a technology choice that could benefit from being documented as an ADR. I'll use the adr-author agent to help capture this architectural decision." <commentary> The user is weighing technology options - a classic ADR-worthy decision. The agent should proactively suggest creating an ADR. </commentary> </example> <example> Context: User mentions a trade-off discussion in a pull request or design review. user: "We debated whether to use REST or GraphQL. We decided on REST because the team knows it better." assistant: "This sounds like an important architectural decision that was made. I'll use the adr-author agent to help document this decision and its rationale." <commentary> A decision has been made with trade-offs. This should be captured in an ADR for future reference. </commentary> </example> <example> Context: User asks about architectural approach for a feature. user: "What's the best way to handle authentication - JWT or session-based?" assistant: "This is an architectural decision that will have long-term implications. Let me use the adr-author agent to help research the options and draft an ADR." <commentary> User is asking about a significant architectural choice. Agent can help research and document. </commentary> </example>

Use this agent proactively to audit code changes against accepted Architectural Decision Records. This agent checks if implementation follows documented architectural decisions and flags violations. Examples: <example> Context: User has written code that might conflict with an accepted ADR. user: "I just implemented the new payment service using direct HTTP calls." assistant: "Let me use the adr-compliance agent to check if this implementation aligns with your accepted ADRs, particularly any decisions about service communication patterns." <commentary> The implementation choice (direct HTTP) might conflict with an ADR about event-driven architecture or async communication. </commentary> </example> <example> Context: User is preparing a pull request with new code. user: "Can you review this PR for architectural compliance?" assistant: "I'll use the adr-compliance agent to audit this code against your accepted architectural decisions." <commentary> Explicit request for architecture compliance review triggers this agent. </commentary> </example> <example> Context: User has made changes to infrastructure or configuration. user: "I added a Redis cache to the order service." assistant: "Let me use the adr-compliance agent to verify this aligns with your caching and infrastructure ADRs." <commentary> Infrastructure changes should be checked against relevant ADRs. </commentary> </example>

Use this agent when researching context, options, or best practices for an architectural decision. This agent analyzes the codebase and searches the web to gather information for ADR authoring. Examples: <example> Context: User needs to research options for a new ADR. user: "I need to write an ADR about choosing a message queue. Can you research the options?" assistant: "I'll use the adr-researcher agent to analyze your codebase for existing patterns and search for best practices on message queues." <commentary> User explicitly needs research for an ADR decision. </commentary> </example> <example> Context: User is gathering context for an architectural decision. user: "What caching patterns do we currently use? I'm considering an ADR about caching strategy." assistant: "I'll use the adr-researcher agent to analyze your codebase for existing caching patterns and gather context for the ADR." <commentary> Research into existing codebase patterns for ADR context. </commentary> </example> <example> Context: User wants to understand industry best practices. user: "What are the pros and cons of event sourcing vs traditional CRUD?" assistant: "I'll use the adr-researcher agent to research event sourcing vs CRUD patterns, including industry best practices and trade-offs." <commentary> Comparative research for architectural decision options. </commentary> </example>

This skill should be used when the user asks about "ADR compliance", "architecture compliance", "ADR audit", "enforce ADRs", "check code against ADRs", "ADR violations", or needs guidance on auditing code compliance with accepted architectural decision records.

This skill should be used when the user asks about "decision drivers", "architectural forces", "quality attributes", "how to identify trade-offs", "non-functional requirements for ADRs", or needs help identifying, documenting, and weighing the forces that influence architectural decisions.

This skill should be used when the user asks about "Alexandrian format", "Alexandrian ADR", "pattern-based ADR", "forces-based ADR", "Christopher Alexander ADR", or needs guidance on creating ADRs using the Alexandrian pattern format.

This skill should be used when the user asks about "business case ADR", "MBA-style ADR", "cost-benefit ADR", "SWOT ADR", "executive ADR", "ROI ADR", or needs guidance on creating ADRs using the business case format for executive and financial analysis.

This skill should be used when the user asks about "MADR format", "MADR template", "Markdown Architectural Decision Records", "MADR 4.0", "MADR sections", or needs guidance on creating ADRs using the MADR (Markdown Architectural Decision Records) format.