Critic Performance — Security agent for Claude Code
Review code for N+1 queries, O(n²)+ algorithmic traps, memory leaks, blocking I/O in async, missing pooling, and resource leaks at scale.
How to install Critic Performance
Installs to ~/.claude/agents/matrixfounder-agentic-development-critic-performance.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/MatrixFounder/Agentic-development/HEAD/.claude/agents/critic-performance.md -o ~/.claude/agents/matrixfounder-agentic-development-critic-performance.md Restart Claude Code, or start a new session, for it to be picked up.
What Critic Performance does
name: critic-performance description: Review code for N+1 queries, O(n²)+ algorithmic traps, memory leaks, blocking I/O in async, missing pooling, and resource leaks at scale. Spawn in parallel with critic-logic and critic-security during /vdd-multi. tools: Read, Grep, Glob
model pin: opus = cost/latency choice for routine critic passes (fable exists above opus — see skill-parallel-orchestration/
references/claude-code.md §Model-pin hygiene); CLAUDE_CODE_SUBAGENT_MODEL env, if set, silen
Alternatives in Security
- JS Error Handler Auditor — Use this agent when you need to audit a JavaScript codebase for unhandled errors in top-level async operations 6.1k ★
- Perf Deep Audit — Use this agent when you need a deep performance review of Electron, React, or Vite-related code — especially f 358 ★
- AI Code Auditor — PYA specialist spawned by the /pya orchestrator 240 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Critic Logic
Review code for logic bugs, unhandled edge cases, happy-path assumptions, input-validation gaps, and error-han
Performance Scale Auditor
Read-only performance & scale specialist. Use proactively during a database audit to analyze indexing, index h
Defect Hunter
Use when one module needs a hunt for latent defects through exactly one lens (correctness, silent failure and
Backend Security Reviewer
Backend security specialist. Use proactively when reviewing or writing server-side code — API endpoints, reque
Perf Complexity Analyzer
Invoke second during a performance audit, after perf-pattern-scanner has produced its findings. Given the scan
Audit Performance
Measures Core Web Vitals (LCP, INP, CLS), Lighthouse scores, and identifies resource optimization opportunitie
Related Skills
RayCodes AIJobSearch
AI Job Search Github: This Local AI Agent Applies to Jobs For You! (Claude Code / Antigravity) - Local-first a
Claude Sessions Duckdb
Query your Claude Code session transcripts with SQL — one DuckDB script, five views, and the format traps that
Dario
A local OpenAI- and Anthropic-compatible proxy that brings your Claude Pro/Max subscription to Cursor, Cline,