Agent

⚡Performance Engineer

Finds and fixes the bottlenecks slowing down your app, database, or infrastructure

What it does

What it does: Runs a measure-first performance workflow: establishes baselines, isolates the real bottleneck, applies targeted optimizations, then validates the improvement under load.

Profiles applications for CPU hotspots, memory allocation, garbage collection, thread contention, and slow async operations
Tunes databases by analyzing execution plans, indexes, connection pooling, lock contention, and caching strategies (including N+1 query problems)
Designs and runs load, stress, spike, and soak tests to model peak traffic and verify scalability
Plans horizontal/vertical scaling, auto-scaling policies, load balancing, sharding, and capacity forecasts
Sets up performance monitoring (RUM, synthetic, APM) with alert thresholds and reports gains as concrete numbers (response time, throughput, resource use, cost)

Installation

1
Make sure Claude is on your device and in your terminal.
Agents load from ~/.claude/agents/ when Claude Code starts. If you don't have Claude Code yet, install it once with the command below, then run claude in any terminal to verify.
One-time setup
```
npm i -g @anthropic-ai/claude-code
```
Already have it? Skip ahead.

Paste into your terminal.

Install

mkdir -p ~/.••••••••••••• •• •••• ••••• ••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••• •• •••••••••••••••••••••••••••••••••••••••••••••••••

Downloads the agent into ~/.claude/agents/performance-engineer-wshobson.md. Safe to re-run; it just overwrites.

Restart Claude Code.
Quit and reopen Claude Code. New agents are picked up on startup.
Use it.
Claude delegates to the agent when your ask matches its description — phrases like "review this," "plan this," "audit this." You can also invoke directly: "Use the performance-engineer-wshobson agent to…"

Prefer to read the source first? Open on GitHub.