Verify+
Invoke AFTER tdd+ or sdd+ implementation is complete. Wraps superpowers:verification-before-completion with evidence standards, spec drift check, and full-suite test run. This is the ONLY phase where full test suite runs are appropriate.
Savings
Report rtk and jcodemunch token savings for the current session.
Verify Harness
Run after `rig init` to verify all hooks, skills, and agents are installed and working correctly in the live session.
Tdd+
Invoke AFTER plan+ is approved. Wraps superpowers:test-driven-development with full-loop assertions, real-dependency enforcement for stack/integration-layer tests, zero-defect, stale test detection, and scoped test runs. Implements plan tasks with RED-GREEN-REFACTOR discipline.
Sdd+
Invoke AFTER plan+ is approved, as an alternative to tdd+ for plans with independent tasks. Wraps superpowers:subagent-driven-development with typed agent dispatch: fresh implementer subagent per task, then spec-reviewer and code-reviewer subagents. Executes the whole plan without pausing between tasks.
Debug+
Invoke when debugging, fixing bugs, diagnosing failures, or when something is broken, unexpected, or not working as expected. Trigger phrases: 'debug', 'fix bug', 'why is X failing', 'what's wrong with', 'broken', 'diagnose', 'investigate'. Wraps superpowers:systematic-debugging with mandatory scout context harvesting.
Plan+
Invoke AFTER brain+ design is approved. Wraps superpowers:writing-plans with constitutional rules, testing strategy per task, and mock policy. Creates bite-sized implementation plans.
Investigate
Alias for debug+. Invoke when encountering any bug, test failure, or unexpected behavior. Redirects to debug+ which wraps superpowers:systematic-debugging with scout agent context.
Review+
Invoke AFTER verify+ passes. Wraps superpowers:requesting-code-review with constitutional compliance checklist, stale test validation, and reviewer agent invocation. Two-stage review: spec compliance + code quality.
Brain+
Invoke BEFORE any design or feature work. Wraps superpowers:brainstorming with scout agent context harvesting, signal-first design considerations, opt-in agent-loop trajectory elicitation, and constitutional rule awareness. Asks questions one at a time to refine the design.