# performance-optimizer

The performance-optimizer subagent finds system bottlenecks and helps tune resource distribution, load balancing, and computational performance.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 850 repo stars
- Author: ruvnet
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ruvnet/agentic-flow/tree/HEAD/.claude/agents/sublinear/performance-optimizer.md
- Updated: 2026-10-26
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/ruvnet-performance-optimizer

## What it does

performance-optimizer examines CPU, memory, network, and storage usage to locate system bottlenecks. It can profile performance, assess scaling limits, tune resource allocation, and suggest changes to load balancing or cache behavior.

The subagent works with the MCP tools `mcp__sublinear-time-solver__solve`, `mcp__sublinear-time-solver__analyzeMatrix`, `mcp__sublinear-time-solver__estimateEntry`, and `mcp__sublinear-time-solver__validateTemporalAdvantage`. These tools cover allocation problems, matrix analysis, metric estimation, and validation of an optimization result.

Its workflow depends on those MCP tools, so their availability matters before the agent runs. The supplied scenarios also cover agent monitoring and resource distribution in Claude Flow. For Flow Nexus, the example creates a Python sandbox with `numpy`, `scipy`, `psutil`, and `prometheus_client`.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/performance-optimizer.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/performance-optimizer.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/performance-optimizer.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/ruvnet/agentic-flow/tree/HEAD/.claude/agents/sublinear/performance-optimizer.md

## When to use it
- locate CPU, memory, network, or storage bottlenecks
- allocate compute resources under constraints
- balance workloads across compute nodes
- assess system scaling limits
- validate changes against original metrics

## Example prompts
- Analyze this system’s CPU, memory, network, and storage usage and identify the bottlenecks.
- Distribute these workloads across the available nodes according to their capacities.
- Compare the original and optimized metrics and validate the performance change.

## Similar
- [commands-performance-optimization](https://affpapa.org/en/nevibecode/plugins/commands-performance-optimization.md) — plugin · ★ 3785 repo stars
- [nginx-config-optimizer](https://affpapa.org/en/nevibecode/skills/nginx-config-optimizer.md) — skill · 457 installs
- [azure-traffic-manager](https://affpapa.org/en/nevibecode/skills/azure-traffic-manager.md) — skill · 178 installs
- [setup-cdn-optimization](https://affpapa.org/en/nevibecode/commands/buildwithclaude-community-setup-cdn-optimization.md) — command · ★ 3785 repo stars
- [react-performance-optimizer](https://affpapa.org/en/nevibecode/agents/react-performance-optimizer.md) — subagent · 2081 installs
- [graphql-performance-optimizer](https://affpapa.org/en/nevibecode/agents/graphql-performance-optimizer.md) — subagent · 599 installs

## Other versions with the same name
- [performance-optimizer · openai](https://affpapa.org/en/nevibecode/agents/performance-optimizer.md) — ★ 8052 repo stars

From the same set: [ruvnet/agentic-flow](https://affpapa.org/en/nevibecode/by/ruvnet/agentic-flow.md) — 76 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
