broneq

Generate conventional commit message based on git changes

Audit a system prompt or skill file against agent-architecture best practices. Returns scored findings; rewrite is opt-in.

Debug issues through structured investigation, failing test creation, and targeted fixes. Use when the user provides an error message, traceback, steps-to-reproduce, or describes unexpected behavior.

Generate comprehensive architecture documentation for complex code modules with Graphviz diagrams and examples. Use when user asks to "explain this code", "document the architecture", or wants to understand how a module/system works.

Lint a BDK agent file for best practices and portability. Use when reviewing, creating, or editing an agent (agents/*.md) to verify it meets BDK conventions. Trigger on phrases like "check this agent", "verify agent", "lint agent", or when about to commit a new agent.

Tool-tier guidance for impact analysis (blast radius, affected flows). Preloaded into agents that reason about change impact; not user-facing.

Rigid TDD process for writing and verifying tests before implementation. Use when implementing any feature or bugfix. Receives test case bullet points from the plan and enforces red-green cycle.

Tool-tier guidance for symbol search and call/reference tracing. Preloaded into agents that locate code; not user-facing.

Run code review with dynamic agent scaling (3-13 agents based on change size)

Tool-tier guidance for codebase exploration and architecture overview. Preloaded into agents that explore code structure; not user-facing.

Create Architecture Decision Records (ADRs) based on MADR template. Use when the user asks to "create an ADR", "document a decision", "write an ADR", or provides decision context that needs to be formalized.

Initialize .bdk/settings.json for this project. Run once per project when BDK blocks session start with missing settings.

Compile Graphviz diagrams (.dot files) to SVG in-place. Use when working with .dot files or markdown with Graphviz code blocks, or when user says "compile diagrams", "generate SVG from dot files", "update documentation diagrams".

Lint a BDK skill or agent file for best practices and portability. Use when reviewing, creating, or editing a skill (skills/*.md) or agent (agents/*.md) to verify it meets BDK conventions. Trigger on phrases like "check this skill", "verify agent", "does this follow best practices", "lint skill", or when about to commit a new skill/agent.

Create comprehensive implementation plan with exploration and trade-off analysis

Execute an implementation plan, then run tests and static analysis, fixing issues

Design pattern principles (GoF, anti-patterns, pattern documentation). Preloaded into agents that propose or review code structure; not user-facing.

Architecture principles (layering, boundaries, dependency direction). Preloaded into agents that reason about structure; not user-facing.

Tool-tier guidance for code review (change detection, risk scoring, review context). Preloaded into reviewer subagents; not user-facing.

Code-quality principles (language-agnostic). Preloaded into agents that write or review code; not user-facing.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Propose better object-oriented architecture for complex, procedural code

Save current work progress to .bdk/save-progress/ for resuming in a future session. Use when context is large, work is in progress, and you want to stop and continue later.

Use when existing architecture documentation needs refreshing after code changes, when running periodic doc maintenance, or when user asks to "update docs", "refresh documentation", or "sync docs with code".

Restore saved work progress from .bdk/save-progress/ to resume a previous session. Loads referenced plans, creates TaskList items for remaining work.

Coordinator that executes a plan in parallel groups via background subagents. Spawns implementers, then dedicated test-runner / static-analyse subagents, then routes failures back to the original implementer (SendMessage) or a fresh fixer. Fully autonomous — no human-in-loop.

Verify implementation plans before execution using a 4-agent pipeline. Use when you have a written plan (from /bdk:create-plan or manual) and want to check if it will actually work before writing code.