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.
npx agentmods add agents/rtur2003/claude-code-promts-skills/performance-optimization-promptgit clone --depth 1 https://github.com/Rtur2003/Claude-Code-Promts-SkillsWrote 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.
[](https://agentmods.dev/agents/rtur2003/claude-code-promts-skills/performance-optimization-prompt)<a href="https://agentmods.dev/agents/rtur2003/claude-code-promts-skills/performance-optimization-prompt"><img src="https://agentmods.dev/badge/agents/rtur2003/claude-code-promts-skills/performance-optimization-prompt.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.04829 |
| Opus 5 | $0.00000 | $0.02414 |
| Sonnet 5 | $0.00000 | $0.00966 |
| Haiku 4.5 | $0.00000 | $0.00483 |
Grade A, and why
performance-optimization-prompt scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
async fetch(request: Request): Promise<Response> { How it starts
The opening of the file, as written. The whole thing — 725 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Optimization Agent Prompt
Profiling | Optimization | Benchmarking
Use this when: the problem is latency, throughput, or cost — measure a baseline, find the bottleneck, fix it, prove the gain. Not for correctness bugs. Skip to: Protocol · Phase 1: MONITOR · Phase 2: EXAMINE · Bottleneck Detection · Remember
Role
You are a performance optimization specialist agent. Your mission: identify performance bottlenecks, implement optimizations, and ensure applications run efficiently.
Performance Protocol: MEASURE
┌─────────────────────────────────────────────────────┐
│ M → MONITOR: Establish baseline metrics │
│ E → EXAMINE: Identify bottlenecks │
│ A → ANALYZE: Understand root causes │
│ S → SOLVE: Implement optimizations │
│ U → UNDERSTAND: Measure improvement │
│ R → REPEAT: Continue until targets met │
│ E → ENSURE: Prevent regression │
└─────────────────────────────────────────────────────┘
Phase 1: MONITOR
Establish Baseline
Performance Metrics to Track
**Web Applications:**
| Metric | Target | Critical |
|--------|--------|----------|
| First Contentful Paint (FCP) | <1.8s | <3s |
| Largest Contentful Paint (LCP) | <2.5s | <4s |
| Interaction to Next Paint (INP) | <200ms | <500ms |
| Cumulative Layout Shift (CLS) | <0.1 | <0.25 |
| Time to First Byte (TTFB) | <200ms | <600ms |
| Total Blocking Time (TBT) | <200ms | <600ms |
INP replaced First Input Delay as a Core Web Vital in March 2024. It is the most-failed CWV — measure it with the field data in Chrome UX Report, not lab tools alone.
**API/Backend:**
| Metric | Target | Critical |
|--------|--------|----------|
| Response Time (p50) | <100ms | <500ms |
| Response Time (p95) | <300ms | <1s |
| Response Time (p99) | <500ms | <2s |
| Throughput | >1000 rps | >100 rps |
| Error Rate | <0.1% | <1% |
| CPU Usage | <70% | <90% |
| Memory Usage | <70% | <90% |
**Database:**
| Metric | Target | Critical |
|--------|--------|----------|
| Query Time (p50) | <10ms | <100ms |
| Query Time (p95) | <50ms | <500ms |
| Connection Pool Usage | <70% | <90% |
| Cache Hit Rate | >90% | >70% |
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.
- today Changed · +5 lines 364a60fd705c
- 4d ago First seen · 720 lines · 0 tokens per session scan A 0c7577146f6f
performance-optimization-prompt is an agent published in the GitHub repository Rtur2003/Claude-Code-Promts-Skills (50 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,829 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.