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 skills/khanh-vu/claude-force/performance-optimization-patternsnpx skills add khanh-vu/claude-force --skill performance-optimization-patternsgit clone --depth 1 https://github.com/khanh-vu/claude-forceWhat 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 | $0.04105 |
| Opus 5 | $0.00000 | $0.02053 |
| Sonnet 5 | $0.00000 | $0.00821 |
| Haiku 4.5 | $0.00000 | $0.00411 |
Grade A, and why
performance-optimization-patterns 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const fetchPromise = fetch(event.request).then((networkResponse) => { How it starts
The opening of the file, as written. The whole thing — 651 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Optimization Patterns
Comprehensive patterns and techniques for optimizing Core Web Vitals (LCP, INP, CLS) and overall web performance.
Core Web Vitals Optimizer
from typing import Dict, List
import json
class CoreWebVitalsOptimizer:
"""Analyze and optimize Core Web Vitals"""
def __init__(self):
self.thresholds = {
"lcp": {"good": 2.5, "needs_improvement": 4.0},
"inp": {"good": 200, "needs_improvement": 500},
"cls": {"good": 0.1, "needs_improvement": 0.25},
}
def analyze_lcp(self, lcp_value: float) -> Dict:
"""
Analyze LCP (Largest Contentful Paint) and provide recommendations
Good: < 2.5s | Needs Improvement: 2.5-4.0s | Poor: > 4.0s
"""
recommendations = []
if lcp_value > self.thresholds["lcp"]["good"]:
recommendations.extend([
{
"priority": "high",
"issue": "Slow LCP",
"recommendations": [
"Optimize largest image (use WebP/AVIF format)",
"Implement CDN for faster asset delivery",
"Preload critical resources with <link rel='preload'>",
"Remove render-blocking resources",
"Use server-side rendering (SSR) for above-fold content",
"Optimize server response time (TTFB < 600ms)",
"Implement lazy loading for below-fold images"
]
}
])
status = self._get_status(lcp_value, "lcp")
return {
"metric": "LCP",
"value": lcp_value,
"unit": "seconds",
"status": status,
"recommendations": recommendations
}
def analyze_inp(self, inp_value: float) -> Dict:
"""
Analyze INP (Interaction to Next Paint) and provide recommendations
Good: < 200ms | Needs Improvement: 200-500ms | Poor: > 500ms
"""
recommendations = []
if inp_value > self.thresholds["inp"]["good"]:
recommendations.extend([
{
"priority": "high",
"issue": "Slow INP",
"recommendations": [
"Reduce JavaScript execution time",
"Implement code splitting to reduce bundle size",
"Defer non-critical JavaScript",
"Use web workers for heavy computations",
"Optimize event handlers and listeners",
"Debounce/throttle expensive operations",
"Break up long tasks (< 50ms chunks)",
"Optimize third-party scripts"
]
}
])
status = self._get_status(inp_value, "inp")
return {
"metric": "INP",
"value": inp_value,
"unit": "milliseconds",
"status": status,
"recommendations": recommendations
}
def analyze_cls(self, cls_value: float) -> Dict:
"""
Analyze CLS (Cumulative Layout Shift) and provide recommendations
Good: < 0.1 | Needs Improvement: 0.1-0.25 | Poor: > 0.25
"""
recommendations = []
if cls_value > self.thresholds["cls"]["good"]:
recommendations.extend([
{
"priority": "high",
"issue": "High CLS",
"recommendations": [
"Set explicit width and height on images and videos",
"Reserve space for ads and embeds",
"Avoid inserting content above existing content",
"Use CSS aspect-ratio for responsive media",
"Preload fonts to prevent FOIT/FOUT",
"Use font-display: swap for web fonts",
"Avoid animations that trigger layout shifts"
]
}
])
status = self._get_status(cls_value, "cls")
return {
"metric": "CLS",
"value": cls_value,
"unit": "score",
"status": status,
"recommendations": recommendations
}
def _get_status(self, value: float, metric: str) -> str:
"""Determine if metric passes/fails"""
threshold = self.thresholds[metric]
if value <= threshold["good"]:
return "good"
elif value <= threshold["needs_improvement"]:
return "needs_improvement"
else:
return "poor"
def generate_optimization_plan(self, vitals: Dict) -> Dict:
"""Generate complete optimization plan"""
plan = {
"lcp": self.analyze_lcp(vitals.get("lcp", 0)),
"inp": self.analyze_inp(vitals.get("inp", 0)),
"cls": self.analyze_cls(vitals.get("cls", 0))
}
# Overall status
statuses = [plan["lcp"]["status"], plan["inp"]["status"], plan["cls"]["status"]]
if all(s == "good" for s in statuses):
plan["overall_status"] = "passing"
elif any(s == "poor" for s in statuses):
plan["overall_status"] = "failing"
else:
plan["overall_status"] = "needs_improvement"
return plan
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.
- 3d ago First seen · 651 lines · 0 tokens per session scan A c4753840cef8
performance-optimization-patterns is a skill published in the GitHub repository khanh-vu/claude-force (5 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,105 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…