Plugin
memorydetective
Hunt iOS memory leaks and investigate runtime performance from inside Claude Code. memorydetective bundles an MCP server with 28 tools for analyzing .memgraph and .trace files, plus a /perf-investigate skill that routes you to the right playbook based on symptoms (leak, hang, jank, slow launch). Key features: - 34-pattern retain-cycle classifier covering SwiftUI (incl. @Observable, SwiftData, NavigationStack), Swift Concurrency, Combine, UIKit, Core Data, RxSwift, Realm, and Coordinator pattern - Every classification ships fixHint + staticAnalysisHint + a Swift before/after fixTemplate snippet - Trace analysis: hangs, animation hitches, allocations, app launch, time profile - compareTracesByPattern for CI gating against perf regressions - 5 SourceKit-LSP-backed Swift source-bridging tools (find references, hover, definitions) - macOS unified logging (logShow / logStream) - 5 slash commands for direct invocation: /investigate-leak, /investigate-hangs, /investigate-jank, /investigate-launch, /verify-cycle-fix Reads memgraphs exported from Xcode's Memory Graph Debugger and traces from xctrace. Ships as both a Claude Code plugin and a standalone npm package, so the same MCP server works in Cursor, Cline, Claude Desktop, and Continue.
- Analysed
- Last observed
What the code does
Static analysis found none of the capabilities we track, such as shell commands, network requests or file writes, in the latest version.
Having a capability is not wrongdoing; many tools need these to do their job. It tells you what to check before you install.
This is public metadata, not a safety certification or complete assessment. Static analysis cannot establish what a tool does at runtime.
Risk
Sign in to see this tool's overall risk level and what drives it. Free.
Coverage
Detailed report
1 finding from automated static analysis of the latest version, with severities and explanations.
Using this tool across your team? We can assess your whole inventory.
Request an inventory assessment