trace

Verify turns uncertain claims into concrete proof by running existing tests, type checks, and targeted validation commands. It reports exactly what passed, what failed, and what remains unverified—ensuring changes are genuinely complete before you move on.

UltraQA automates the test-fix loop by running quality checks, analyzing what broke, and applying corrections across up to 5 cycles. Choose your goal—tests, build, lint, or type checking—and let it work toward success. It tracks progress, detects repeated failures, and exits when the goal is met or max cycles reached.

Status displays which OMG mode is running and reports its current progress, including active phases, task completion, and agent states. Use it to verify what's executing, monitor advancement through workflows, or confirm state after resuming operations.

H Abduct runs a structured four-step abductive cycle to generate ≥3 competing typed hypotheses for an observed signal, applying plausibility filters and surfacing the prime candidate alongside rivals. It's designed as an internal subroutine for h-diagnose's parallel testing, though manual invocation is supported when disciplined abduction without parallel overhead is needed.

Parallel Debugging applies the Analysis of Competing Hypotheses methodology to organize multi-agent investigation of complex issues. It structures hypothesis generation across six failure mode categories, establishes evidence collection standards with citation requirements, and provides arbitration protocols to identify root causes while avoiding confirmation bias.

This skill teaches you to trace bugs backward through the call chain rather than fixing where errors appear. By working systematically up the stack—identifying what called each function and what values were passed—you locate the original trigger and fix the root cause. Includes instrumentation techniques, stack trace analysis, and real examples of finding pollution across test suites.