# v3-performance-engineer

v3-performance-engineer — a subagent that benchmarks claude-flow v3 and pushes it toward stated goals: Flash Attention, HNSW search, cold start, memory. Use it when the numbers are claimed and need proving.

- 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/v3/v3-performance-engineer.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/v3-performance-engineer

## What it does

Ships with ruvnet/agentic-flow. The job is to hit hard numbers on claude-flow v3: Flash Attention speedup in the 2.49x–7.47x band, AgentDB HNSW search 150x–12,500x faster than the linear pass, memory down by 50–75%, cold start under 500ms, SONA adaptation under 0.05ms.

Four benchmark groups come along. Cold start times the CLI, the MCP server and agent spawn. Search runs 10000 queries through both the old linear lookup and HNSW, then divides one by the other. Memory reads the heap before and after compression. Swarm coordination spawns 15 agents and times task decomposition plus consensus. Attention is measured on 512, 1024, 2048 and 4096 token sequences.

Both hooks are plain shell. The pre-hook prints the target list and checks whether `npm` and `node` exist on the machine. The post-hook saves a pattern with `npx agentic-flow@alpha memory store-pattern`, and a failure there is swallowed by `|| true` — the run still finishes when npm is unreachable, you just lose the stored pattern.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/v3-performance-engineer.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/v3-performance-engineer.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/v3-performance-engineer.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/v3/v3-performance-engineer.md

## When to use it
- Benchmark cold start for the CLI, MCP server and agent spawn
- Compare HNSW search against linear lookup on 10000 queries
- Measure heap use before and after compression
- Time 15-agent swarm coordination and consensus
- Validate Flash Attention on long sequences

## Example prompts
- Run v3-performance-engineer and benchmark cold start for the CLI and the MCP server.
- Compare linear search with HNSW on 10000 queries and show the speedup.
- Check Flash Attention on 512, 1024, 2048 and 4096 token sequences and store the result.

## Similar
- [performance-engineer](https://affpapa.org/en/nevibecode/agents/ngophatneknha-performance-engineer.md) — subagent · ★ 189 repo stars
- [performance-analysis](https://affpapa.org/en/nevibecode/skills/performance-analysis.md) — skill · 1200 installs
- [V3 Performance Optimization](https://affpapa.org/en/nevibecode/skills/v3-performance-optimization.md) — skill · 1100 installs
- [performance-monitor](https://affpapa.org/en/nevibecode/plugins/performance-monitor.md) — plugin · ★ 2858 repo stars
- [agent-performance-engineer](https://affpapa.org/en/nevibecode/skills/agent-performance-engineer.md) — skill · 556 installs
- [CPU Performance Engineering](https://affpapa.org/en/nevibecode/mcp/cpu-performance-engineering.md) — MCP server · ★ 1160 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
