Skip to main content
subagent CX Codex

v3-performance-engineer — Claude Code subagent: performance targets

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.

no license ★ 850 updated 2026-10-26

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/v3-performance-engineer.md
Open on GitHub

What v3-performance-engineer 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.

What it helps with

  • 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 for the agent

  • 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.

How to install v3-performance-engineer

Manually: put the files in place

.claude/agents/v3-performance-engineer.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about v3-performance-engineer

How do I install v3-performance-engineer in Claude Code?

Take the agent file from ruvnet/agentic-flow and place it in your project at .claude/agents/v3-performance-engineer.md.

What does v3-performance-engineer do?

It benchmarks claude-flow v3 and checks the results against a target matrix covering Flash Attention, HNSW search, memory, cold start and swarm coordination.

What does the subagent need to run?

The pre-hook looks for npm and node; the post-hook calls npx agentic-flow@alpha memory store-pattern. Without reachable npm the pattern is not saved, but the run itself completes.

Similar subagents

All subagents for Agent setup: memory, context, orchestration →

From the same set76

The whole set →
supabase-admin supabase-admin — a Claude command that puts the agent in charge of Supabase: Postgres schemas, RLS policies, auth and storage buckets, all through the MCP server rather than the CLI. CX Codex +1 ★ 850repo stars ml-developer ml-developer — a dedicated subagent for training machine learning models, exploring hyperparameter spaces, and editing Jupyter notebooks. CX Codex ★ 850repo stars Load Balancing Coordinator The Load Balancing Coordinator subagent assigns work according to agent load and task priority. Use it to manage queues or move work away from overloaded agents. CX Codex ★ 850repo stars release-swarm release-swarm is a Claude Code command for planning releases from commits and merged pull requests, preparing changelogs, and coordinating publication through GitHub CLI. CX Codex +1 ★ 850repo stars multi-repo-swarm multi-repo-swarm — a subagent for Claude Code that orchestrates multiple agents across your organization's repositories. Runs synchronized tasks, manages dependencies, and links pull requests between projects. CX Codex ★ 850repo stars consensus-coordinator consensus-coordinator — a Claude subagent that computes distributed consensus: Byzantine fault tolerance, voting and agreement across an agent swarm. CX Codex ★ 850repo stars specification SPARC specification subagent for requirements analysis. Gathers acceptance criteria, outlines project scope, and learns from previous patterns via claude-flow. CX Codex ★ 850repo stars pr-manager pr-manager coordinates pull request reviews, tests, and merge work through GitHub tools and a swarm of agents. It can also reuse patterns saved from earlier PR tasks. CX Codex ★ 850repo stars

Project sponsors

Companies that keep this analytics open