audit-memory-retention
Analyze reference retention paths that prevent GC of removed entries
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Analyze reference retention paths that prevent GC of removed entries
Audit hot paths for performance inefficiencies (allocations, contention, layout)
Analyze user callbacks for re-entrancy defects (deadlock, corruption)
Audit serialization proxy correctness and round-trip safety
Differential audit comparing matched code paths that should behave identically. Spawns one auditor per sibling pair (sync/async, bounded/unbounded, view consistency, bulk vs single, generated node variants, read fast vs slow, adapter conformance) and requires a concrete witness scenario where the two paths diverge observably.
Audit explicit state machines (drain status, node lifecycle, async-value lifecycle) for illegal or missed transitions
Audit one cache subsystem for concurrency correctness defects
Heavyweight history-mining bug audit. Walks the caffeine module's git history chronologically (oldest to HEAD), maintains a forward-tracked issue database, and surfaces concerns introduced by past commits that were never resolved. Catches bugs that snapshot mining cannot — half-fixes invisible from current state, latent+trigger pairs across multi-commit interactions, and partial refactors. Slow (model/effort-dependent; ~24h on Opus + max effort) and rare-run (every several months or before a major release).
Multi-layer adversarial code review of a diff or branch using parallel specialized reviewers with triage
Analyze a cache trace file to understand its characteristics and recommend policies