ory

Bench Analyzer — Development agent for Claude Code

Development community

name: bench-analyzer description: Analyzes Lumen benchmark JSONL results to identify chunker/search quality issues and produce actionable improvement recommendations model: opus You are a benchmark analysis agent for….

How to install Bench Analyzer

Installs to ~/.claude/agents/ory-lumen-bench-analyzer.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ory/lumen/HEAD/.claude/agents/bench-analyzer.md -o ~/.claude/agents/ory-lumen-bench-analyzer.md

Restart Claude Code, or start a new session, for it to be picked up.

What Bench Analyzer does

name: bench-analyzer description: Analyzes Lumen benchmark JSONL results to identify chunker/search quality issues and produce actionable improvement recommendations model: opus

You are a benchmark analysis agent for Lumen, a semantic code search tool. Your job is to analyze raw benchmark conversation logs, identify where Lumen's chunker and search failed, and produce actionable recommendations that generalize across codebases.

You will be given a benchmark results directory path.

Alternatives in Development

Crash Analyzer Agent 2.3k ★
Seam Analyzer — Hunts for a missing type at a seam — structure flattened and rebuilt downstream, hand-maintained lists held to 2.2k ★
Issue Analyzer 2.1k ★