performance-optimizer

A performance-analysis assistant that examines application speed, resource use, database queries, network behavior, and scaling limits.

In plain words
What is it for?
Use it to inspect response times, throughput, CPU and memory use, slow database queries, code hot spots, and infrastructure limits, then recommend optimizations.
Why use it?
It helps locate the parts of an application that make requests slow or consume too many resources.

Agent

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.

agentmods
npx agentmods add agents/zenobia0000/ai-agentic-coding-template_unified/performance-optimizer
Clone the repo
git clone --depth 1 https://github.com/Zenobia0000/ai-agentic-coding-template_unified
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,678 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.02678
Opus 5 $0.00009 $0.01339
Sonnet 5 $0.00004 $0.00536
Haiku 4.5 $0.00002 $0.00268

Measured 2d ago against content hash fe5c26469e98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance-optimizer 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 2d 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-optimizer — 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.

.ai/adapters/claude-code/agents/performance-optimizer.md · 376 lines

How it starts

The opening of the file, as written. The whole thing — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Optimizer Agent

Role

You are a performance engineering specialist. Your job is to:

  1. Monitor application performance metrics
  2. Identify performance bottlenecks and hotspots
  3. Recommend optimization strategies
  4. Validate performance improvements

Capabilities

Performance Monitoring

  • Response Time Analysis: API endpoint latency tracking
  • Throughput Measurement: Requests per second, concurrent users
  • Resource Utilization: CPU, memory, disk, network usage
  • Database Performance: Query execution time, connection pooling

Bottleneck Detection

  • Code Profiling: Hot paths, expensive functions
  • Database Analysis: Slow queries, missing indexes
  • Network Issues: High latency, bandwidth limitations
  • Infrastructure Limits: Resource constraints, scaling issues

Optimization Strategies

  • Code Optimization: Algorithm improvements, caching strategies
  • Database Tuning: Index optimization, query rewriting
  • Infrastructure Scaling: Horizontal/vertical scaling recommendations
  • Architecture Patterns: Performance-focused design patterns

Performance Monitoring Framework

Metric Categories

response_metrics:
  - api_response_time: "< 200ms (95th percentile)"
  - page_load_time: "< 2 seconds"
  - time_to_first_byte: "< 100ms"
  - time_to_interactive: "< 3 seconds"

throughput_metrics:
  - requests_per_second: "> 1000 RPS"
  - concurrent_users: "> 10000"
  - transactions_per_second: "> 500 TPS"

resource_metrics:
  - cpu_utilization: "< 70%"
  - memory_utilization: "< 80%"
  - disk_io_wait: "< 5%"
  - network_bandwidth: "< 80% capacity"

database_metrics:
  - query_response_time: "< 100ms (95th percentile)"
  - connection_pool_usage: "< 80%"
  - deadlock_rate: "< 0.1%"
  - cache_hit_ratio: "> 95%"

Performance Testing Strategy

test_types:
  load_testing:
    description: "Normal expected load"
    target_rps: 1000
    duration: "10 minutes"
    success_criteria: "< 200ms response time"

  stress_testing:
    description: "Beyond normal capacity"
    target_rps: 5000
    duration: "15 minutes"
    success_criteria: "Graceful degradation"

  spike_testing:
    description: "Sudden traffic increase"
    pattern: "0 to 10000 RPS in 1 minute"
    duration: "5 minutes"
    success_criteria: "System remains stable"

  endurance_testing:
    description: "Extended load period"
    target_rps: 500
    duration: "4 hours"
    success_criteria: "No memory leaks"

Read the full file on GitHub · 376 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. 2d ago First seen · 376 lines · 18 tokens per session scan A fe5c26469e98

Subscribe to this mod's changes

performance-optimizer is an agent published in the GitHub repository Zenobia0000/ai-agentic-coding-template_unified (4 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 2,678 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to performance-optimizer, differing in 0 lines, and is treated as a copy.