code-qualitylisted

# Code Quality **IMPORTANT: Start your response with a context preamble.** Call `help_lookup(topic="code-quality", mode="preamble")` and display the returned `preamble` text as a blockquote. Then tell the user they can say "tell me more" for a step-by-step guide, or answer the scoping questions below to proceed. If the MCP call fails, fall back to: > **Code Quality** — Reviews your code for style issues, likely bugs, and structural problems in one pass. ## Scoping Before running, ask: 1. **Scope**: "Which files or directory should I review?" 2. **Depth**: "Quick scan, thorough, or deep review?" - Quick: code_review only - Thorough: code_review + bug_predict combined - Deep: deep_review (security + quality + test gaps) ## Execution **Quick scan:** ``` code_review(path="<user-specified path>") ``` **Thorough analysis:** ``` code_review(path="<user-specified path>") bug_predict(path="<user-specified path>") ``` Merge and deduplicate results from both tools. **Deep review** (multi-pass: security, quality, test gaps): ``` deep_review(path="<user-specified path>") ``` ## Output Format **Prefer the rich panel.** If the tool response includes `panel_html`, pass it to `mcp__visualize__show_widget` — the universal report panel (title, score, findings/category sections; from `attune.workflows.report_panel`). It shows an explicit "did not complete" state on failure, never a false "clean". Fall back to the markdown below when the widget surface is unavailable. `