Performance Benchmarker — Development agent for Claude Code
Use for designing and running performance benchmarks with actionable reporting.
How to install Performance Benchmarker
Installs to ~/.claude/agents/dnyoussef-context-cascade-performance-benchmarker.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/DNYoussef/context-cascade/HEAD/agents/performance-benchmarker.md -o ~/.claude/agents/dnyoussef-context-cascade-performance-benchmarker.md Restart Claude Code, or start a new session, for it to be picked up.
What Performance Benchmarker does
name: performance-benchmarker description: "Use for designing and running performance benchmarks with actionable reporting." tools:
- Read
- Edit
- Write
- Bash model: inherit permissionMode: default
Library-First Directive
This agent operates under library-first constraints:
- Pre-Check Required: Before writing code, search:
.claude/library/catalog.json(components).claude/docs/inventories/LIBRARY-PATTERNS-GUIDE.md(patterns)D:\Projects\*(e
Alternatives in Development
- Dao Qi Harmony Designer — This agent should be used when designing, evaluating, or refining software products to ensure harmony between 5.2k ★
- Compass Planner — Use this agent when the user needs a structured work plan from a vague idea, when they say 'plan this' or 'let 523 ★
- Recall — Runs the recall CLI over the user's past Claude Code sessions and returns the one actionable item — a command 204 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
MCP Developer
Expert in MCP protocol, FastMCP 2.0+ framework, and Python/TypeScript. Use for implementing/reviewing MCP serv
Fk Benchmarker
Owns the measurement protocol - noise floor, warm-up, clock ramp, repeats, CUDA sync, peak VRAM, launch counts
Fk Orchestrator
Runs the fast-kernel optimization loop for a campaign and coordinates the other agents (profiler, kernel engin
Bench Runner
Executes a11y skill benchmarks across hosted and local model families. Runs cloud/Codex/Ollama benchmark scrip
Financial Estimator
Produces a defensible size read on private companies that publish nothing — revenue and EBITDA ranges from hea
Outreach Analyst
Campaign analyst. Reads one campaign's statistics and activity feed from Emelia, computes the rates on stated
Related Skills
App Paywall Pilot
A framework for designing App Store-compliant subscription paywalls. 4 layers: AI skill (Claude/GPT/Cursor) +
Bench
Run performance benchmarks for RLM-Claude-Code.
Gql Performance Benchmark
Run GraphQL performance benchmarks against the Alkemio API and compare against a stored baseline