Use when the user asks to audit, review, investigate, check, scan, "look at", or "find issues in" code — anything that sounds like a diagnostic request without an explicit fix authorization. Enforces findings-only output with severity tiering, forbids in-place fixes during audit, and blocks the…
Structured debugging protocol. Use when investigating a bug, failing test, regression, unexpected behavior, or any scenario where code is not doing what it should. Trigger phrases include "broken", "not working", "bug", "error", "it worked before", "still broken", "why is this failing", "trace", or "/trace".
Use when reviewing whether module boundaries earn their keep — finding shallow modules that should be consolidated into deep ones. Triggers on phrases like "is this over-modularised?", "should these be one module?", "too many small files doing related work", "interface feels as complex as implementation", "review the…
Auto-detects the project's tech stack, then audits for Accessibility, Performance, and Code Quality. Works across WordPress/PHP, Python, Node/JS, and static web projects.
Review auto-memory for the current project. Shows accumulated learnings, identifies noise, and helps promote permanent patterns to CLAUDE.md, rules, or skills.
Use when reviewing Swift 5.5+ code containing await, actor, Task { }, @MainActor, @unchecked Sendable, cancellable timer/deadline handles, or long-lived for await AsyncStream consumers — especially diffs extending existing actors with new methods. Catches post-await state-overwrite races, TOCTOU around Task spawn…
Generate a user-facing test checklist from git diff, or execute an existing test plan via Playwright. Two modes: generate (default) creates the plan, execute runs it in the browser.
Recovery protocol for tool failures and search budgets. Use when Edit fails repeatedly on the same target, when hooks may have modified file contents between operations, or when WebSearch/WebFetch is not converging on an answer.
Open an app in Playwright and explore it as a real user with no prior knowledge. Report UX findings per page, test core flows, and suggest improvements.