broneq

cr

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

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.

create-plan

Create comprehensive implementation plan with exploration and trade-off analysis

create-tasks

Write PM-style task definitions (User Story + Given/When/Then ACs) from feature descriptions or code findings. Use when user wants product tasks, epic decomposition, or acceptance criteria. Triggers on "PM tasks", "user story", "epic", "acceptance criteria".

debug

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.

design

Design partner for any feature. Classifies product vs architecture vs combined, then explores 2+ approaches with Mermaid diagrams, self-critique, and a 'what we did NOT decide' section. Replaces /bdk:brainstorming and /bdk:brainstorm-architecture.

execute-plan

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

explain-complex-code

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.

graphviz-docs-compiler

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".

refine-rules

Compact and verify .claude/rules/*.md documentation against the real codebase — strips changelog/history/narration, verifies every checkable claim against current code instead of trusting prior wording, and rewrites every rule file into one uniform format. Use when the user asks to "clean up rules", "compact/refine .claude/rules", "audit our rule docs", says rule files are stale, bloated, or inconsistent, or after many sessions/agents have accreted conflicting or narrative content into .claude/rules/.

save-progress

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.

setup

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

subagent-execute-plan

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.

update-docs

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".

refactor

Propose better object-oriented architecture for complex, procedural code

restore-progress

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

agent-lint

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.

skill-lint

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.

Testing & QA Listed

test-driven-development

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.

verify-plan

Verify implementation plans before execution with a single Opus subagent driven by a structured six-section checklist. Use when you have a written plan (from /bdk:create-plan or manual) and want to check it works before writing code.