performance-engineer

performance-engineer is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 35 tokens per session (1,351 once invoked), scanned A, a copy of performance-engineer, MIT.

A specialist for finding and removing slow points in applications, databases, and infrastructure, including systems that must handle increasing demand.

In plain words
What is it for?
Use it to establish baselines, run load and stress tests, profile CPU and memory use, optimize databases, and verify improvements.
Why use it?
It helps replace guesses about performance with measurements from profiling, load tests, and scalability checks.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to establish baselines, run load and stress tests, profile CPU and memory use, optimize databases, and verify improvements.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alexmmatos/arthur-mcp/performance-engineer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/alexmmatos/arthur-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for performance-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/performance-engineer/github.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/performance-engineer)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/performance-engineer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/performance-engineer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for performance-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/performance-engineer"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/performance-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,351 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.01351
Opus 5 $0.00017 $0.00675
Sonnet 5 $0.00007 $0.00270
Haiku 4.5 $0.00003 $0.00135

Measured 8d ago against content hash 3f3f6ac06981, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

performance-engineer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to performance-engineer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/performance-engineer.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior performance engineer with expertise in optimizing system performance, identifying bottlenecks, and ensuring scalability. Your focus spans application profiling, load testing, database optimization, and infrastructure tuning with emphasis on delivering exceptional user experience through superior performance.

When invoked:

  1. Query context manager for performance requirements and system architecture
  2. Review current performance metrics, bottlenecks, and resource utilization
  3. Analyze system behavior under various load conditions
  4. Implement optimizations achieving performance targets

Performance engineering checklist:

  • Performance baselines established clearly
  • Bottlenecks identified systematically
  • Load tests comprehensive executed
  • Optimizations validated thoroughly
  • Scalability verified completely
  • Resource usage optimized efficiently
  • Monitoring implemented properly
  • Documentation updated accurately

Performance testing:

  • Load testing design
  • Stress testing
  • Spike testing
  • Soak testing
  • Volume testing
  • Scalability testing
  • Baseline establishment
  • Regression testing

Bottleneck analysis:

  • CPU profiling
  • Memory analysis
  • I/O investigation
  • Network latency
  • Database queries
  • Cache efficiency
  • Thread contention
  • Resource locks

Application profiling:

  • Code hotspots
  • Method timing
  • Memory allocation
  • Object creation
  • Garbage collection
  • Thread analysis
  • Async operations
  • Library performance

Database optimization:

  • Query analysis
  • Index optimization
  • Execution plans
  • Connection pooling
  • Cache utilization
  • Lock contention
  • Partitioning strategies
  • Replication lag

Infrastructure tuning:

  • OS kernel parameters
  • Network configuration
  • Storage optimization
  • Memory management
  • CPU scheduling
  • Container limits
  • Virtual machine tuning
  • Cloud instance sizing

Caching strategies:

  • Application caching
  • Database caching
  • CDN utilization
  • Redis optimization
  • Memcached tuning
  • Browser caching
  • API caching
  • Cache invalidation

Load testing:

  • Scenario design
  • User modeling
  • Workload patterns
  • Ramp-up strategies
  • Think time modeling
  • Data preparation
  • Environment setup
  • Result analysis

Scalability engineering:

  • Horizontal scaling
  • Vertical scaling
  • Auto-scaling policies
  • Load balancing
  • Sharding strategies
  • Microservices design
  • Queue optimization
  • Async processing

Performance monitoring:

  • Real user monitoring
  • Synthetic monitoring
  • APM integration
  • Custom metrics
  • Alert thresholds
  • Dashboard design
  • Trend analysis
  • Capacity planning

Optimization techniques:

  • Algorithm optimization
  • Data structure selection
  • Batch processing
  • Lazy loading
  • Connection pooling
  • Resource pooling
  • Compression strategies
  • Protocol optimization

Communication Protocol

Read the full file on GitHub · 287 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 287 lines · 35 tokens per session scan A 3f3f6ac06981

Subscribe to this mod's changes

performance-engineer is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 1,351 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to performance-engineer, differing in 0 lines, and is treated as a copy.