dp-cto

Adversarial spec reviewer for dp-cto. Applies critical lenses to draft specifications. Read-only investigation.

Structured root-cause debugging agent for dp-cto. Investigates errors through 4-phase protocol (reproduce, analyze, hypothesize, verify). Can write minimal repro scripts but does not fix bugs. Use for debug dispatch and ad-hoc debugging.

Implementation agent for dp-cto run. Executes planned tasks with TDD discipline, scope enforcement, and completion receipts. Use for all dp-cto subagent and iterative task dispatch.

Research agent for dp-cto. Performs web research and codebase analysis without file mutation. Use for plan context gathering and any research-heavy dispatch.

Read-only code review agent for dp-cto review skill. Reviews code through specific lenses (security, simplification, test gaps, linting, performance, docs). Use for all dp-cto review dispatch.

Drift detection and entropy management agent for dp-cto review sweep. Detects and fixes dead code, inconsistent patterns, stale comments, and naming violations. Use for all dp-cto sweep dispatch.

Test-writing specialist agent for dp-cto. Writes tests following strict RED-GREEN-REFACTOR discipline. Use for tdd dispatch and ad-hoc test creation.

Read-only validation agent for dp-cto run. Independently verifies builder completion receipts against acceptance criteria. Use for all dp-cto builder/validator reviews.

Use when you need to make a decision, compare options, or think through a list of items systematically — 'help me decide', 'weigh these options', 'walk me through the tradeoffs'.

Use when you hit a bug, test failure, or unexpected behavior and want a structured investigation — 'debug this', 'why is this failing', 'find the root cause'.

Use when you need to look something up, validate a claim, check documentation, or gather evidence before making a decision — 'research this', 'is this true', 'find out how X works'.

Use when you want a code review on recent changes, a specific file, or a pull request — 'review this', 'check my code', 'what did I miss'. Works in any project without setup.

Use when you want to clean up drift, dead code, stale comments, or naming violations — 'sweep this', 'clean up', 'find dead code', 'check for drift'. Standalone entropy scan without an active epic.

Use when discovery is complete and requirements need refinement with solution approaches explored — requires completed discover phase.

Use when a draft spec is ready for adversarial review from multiple critical perspectives — requires completed draft phase.

Use when encountering a bug, error, or failing test that needs structured investigation — 'this is broken', 'why does this fail', 'trace this error'. Enforces diagnosis before any fix attempt.

Use when starting a new spec session to gather constraints, requirements, and boundaries — entry point for the spec pipeline.

Use when research is complete and the PRD needs to be authored — requires completed research phase.

Use when an implementation agent needs to verify claims are grounded in evidence, not generated from memory.

Use when a spec is approved and needs decomposition into scoped implementation tasks — requires completed challenge phase.

Use when you need to pause current work and come back later, or resume previously paused work — 'park this', 'pause the epic', 'pick up where I left off'.

Use when you have clear requirements and want to go straight to implementation planning — task breakdown, dependency ordering, and agent-ready prompts. Use after /dp-cto:spec for specced work, or directly for well-scoped tasks.

Use when you need to validate a technical decision, investigate prior art, check feasibility, or gather evidence — 'is this approach viable', 'what are the alternatives', 'find evidence for this'.

Use when code changes are ready for quality review, after implementation completes, or before committing — 'review this', 'check quality', 'what needs fixing'.

Use when a plan is ready and you want to execute it — 'run the plan', 'start building', 'dispatch the tasks'.

Use when starting major work that needs formal design review — cross-team changes, architectural decisions, or complex features where requirements need discovery before implementation.

Use when you want to write tests first, enforce test-driven development, or add test coverage — 'write tests for this', 'TDD this feature', 'add test coverage'. Strict RED-GREEN-REFACTOR discipline.

18 hooks across 8 events