Impl Performance — Research agent for Claude Code
Reviews implementation plans from a performance and efficiency perspective.
How to install Impl Performance
Installs to ~/.claude/agents/pinecone-io-rings-impl-performance.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/pinecone-io/rings/HEAD/.claude/agents/impl-performance.md -o ~/.claude/agents/pinecone-io-rings-impl-performance.md Restart Claude Code, or start a new session, for it to be picked up.
What Impl Performance does
name: impl-performance model: sonnet description: Reviews implementation plans from a performance and efficiency perspective. Use when evaluating algorithmic complexity, unnecessary allocations, hot path analysis, benchmarking strategy, and whether performance-sensitive operations will scale to realistic workloads.
You think about performance not as micro-optimization but as designing systems that behave acceptably at realistic scale. You know that premature optimization is a real probl
Alternatives in Research
- Attack Tree Construction — Systematic attack path visualization and analysis 31.9k ★
- Council Sun Tzu — Council member 4.2k ★
- Deep Dive — Use this agent when you need comprehensive analysis, investigation, or exploration of code, architecture, or t 1.8k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Application Profiler
Code-level optimization expert with profiling and algorithm optimization expertise. CPU, memory, and algorithm
Aria Hr
Use this agent when dealing with HR and People Operations activities. This includes recruiting pipeline manage
Perf
Performance analysis — N+1 queries, missing eager loading, slow queries, unnecessary re-renders.
Review Code Reproducibility
A code review agent that evaluates whether analysis scripts form a complete, self-contained, and reproducible
Market Iq
Track competitive landscape, produce competitive moat maps and win/loss analysis. Use when evaluating strategi
Realestate Buyers Agent
Champions the buyer through every step of finding, evaluating, and securing their ideal property. Expert in ne
Related Skills
Downside Case
Builds the strongest possible case for NOT building a feature. Acts as a rigorous adversary, evaluating opport
MiniMax M2 Interleaved Thinking
Interactive demo showcasing MiniMax-M2's interleaved thinking for agentic workflows, demonstrating adaptive st
Context Files Coding Agents
Do Context Files Help Coding Agents? Two-agent (Claude Code + Codex) ablation on whether AGENTS.md/CLAUDE.md c