deep-code-reviewerlisted

# Deep Code Reviewer Perform review as an auditor, not as a summarizer. Prioritize findings that can cause incorrect behavior, operational pain, or expensive future changes. ## Quick Start 1. Establish scope before judging details. 2. Inspect surrounding code, not just the diff or pasted snippet. 3. Trace data flow, control flow, state transitions, and failure paths. 4. Produce findings ordered by severity with concrete file references. 5. Keep summaries brief and secondary to the findings. ## Review Workflow ### 1. Build Context Read enough code to understand: - Entry points and callers - State ownership and mutation boundaries - Invariants that must always hold - External dependencies: databases, queues, caches, RPCs, files, clocks, feature flags - Existing tests and what they do not cover If the change touches a framework or subsystem with non-obvious behavior, read the local docs or implementation that defines the contract before concluding. ### 2. Hunt for High-Impact Failures First Check for: - Incorrectness: broken invariants, off-by-one logic, missing validation, bad error handling, partial updates - Concurrency hazards: races, duplicate work, lost updates, stale reads, deadlocks, non-atomic sequences - Security flaws: authorization gaps, trust-boundary violations, secret leakage, injection vectors - Data integrity issues: transaction gaps, mismatched schemas, silent truncation, incompatible migrations - Performance cliffs: N+1 queries, unnecessary allocati