Which worker operations are tested?

The skill tests trigger detection, worker registry CRUD, agent selection, model caching, concurrent execution, and memory key generation.

How do I run a specific benchmark instead of the full suite?

You can use the --type flag followed by the benchmark name, for example: npx agentic-flow workers benchmark --type registry.

Can I set custom performance targets?

Yes, benchmark thresholds can be configured in the .claude.settings.json file to match your specific performance requirements.

What specific metrics does this skill track?

It tracks average and p95 latency, throughput (ops/sec), memory delta, and peak memory usage across various worker operations.

Agentic Worker Benchmarks

Name: Agentic Worker Benchmarks
Author: nbossn

bynbossn

0•

Analytics & Monitoring

Measures and optimizes the performance of agentic-flow worker systems through automated latency and throughput testing.

The Worker Benchmarks skill provides a comprehensive suite of performance testing tools designed to analyze and optimize the agentic-flow ecosystem. It enables developers to quantify trigger detection speed, worker registry operations, agent selection efficiency, and memory key generation. By providing detailed metrics like p95 latency, throughput, and memory delta, this skill helps identify bottlenecks in worker orchestration and ensures that system-wide performance thresholds are met for high-throughput AI agent environments.

Key Features

010 GitHub stars

02Customizable benchmark thresholds via settings configuration

03Detailed latency analysis including p95 and average metrics

04Resource usage tracking including memory delta and peak memory

05Automated performance testing for trigger detection and worker registries

06Throughput measurement for concurrent worker operations

Use Cases

01Identifying performance bottlenecks in complex multi-agent workflows

02Optimizing model caching and concurrent worker execution for production

03Verifying system stability and latency after making configuration changes

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add nbossn/claude-code-base worker-benchmarks

For use in Claude.ai and ChatGPT

Key Features

010 GitHub stars

02Customizable benchmark thresholds via settings configuration

03Detailed latency analysis including p95 and average metrics

04Resource usage tracking including memory delta and peak memory

05Automated performance testing for trigger detection and worker registries

06Throughput measurement for concurrent worker operations

Use Cases

01Identifying performance bottlenecks in complex multi-agent workflows

02Optimizing model caching and concurrent worker execution for production

03Verifying system stability and latency after making configuration changes

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add nbossn/claude-code-base worker-benchmarks

For use in Claude.ai and ChatGPT