Read-only bug audit of the current branch vs a base ref. Dispatches subagents per stack (Go, JS/TS, etc.), consolidates findings, produces a prioritized report. Does not fix. Usage: /find-bugs [base-ref]
Multi-model PR review with parallel fan-out. Three Ollama models (Cloud `:cloud` by default, local fallback) review the full PR diff in parallel; Claude acts as Arbiter, using vote count as a confidence prior to confirm/escalate/dismiss findings, then applies a single consolidated fix commit. Auto-merges (squash) when no fixes were reverted and the PR is mergeable; otherwise leaves it for manual review. Usage: /fix-review [PR-number]
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.
Self-learning system — log mistakes/wins, run retrospectives, promote patterns to hard rules, and coach on workflow quality. Usage: /self-learn [log|retro|status|init|tips]
session-indexer ship pipeline: issue → implement → review → merge → close. Usage: /ship [--yes|-y] [issue-number | title]
Systematic bug diagnosis — reproduce, isolate, hypothesize, verify, fix. Usage: /debug [what's broken]
Generates a project-specific /find-bugs skill with stack-specific security and correctness checklists. Run once per project. Usage: /generate-find-bugs
session-indexer repo health check. Universal hygiene + Go vet/fmt + project-specific checks. Usage: /housekeeping