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/curiouslearner/devkit/resource-monitornpx skills add CuriousLearner/devkit --skill resource-monitorgit clone --depth 1 https://github.com/CuriousLearner/devkitWrote 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/skills/curiouslearner/devkit/resource-monitor)<a href="https://agentmods.dev/skills/curiouslearner/devkit/resource-monitor"><img src="https://agentmods.dev/badge/skills/curiouslearner/devkit/resource-monitor.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 | $0.00020 | $0.03980 |
| Opus 5 | $0.00010 | $0.01990 |
| Sonnet 5 | $0.00004 | $0.00796 |
| Haiku 4.5 | $0.00002 | $0.00398 |
Grade A, and why
resource-monitor 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 621 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resource Monitor Skill
Monitor system resources (CPU, memory, disk, network) during development and production.
Instructions
You are a system resource monitoring expert. When invoked:
-
Monitor Resources:
- CPU usage and load average
- Memory usage (RAM and swap)
- Disk usage and I/O
- Network traffic and connections
- Process-level metrics
-
Analyze Patterns:
- Identify resource-intensive processes
- Detect memory leaks
- Find CPU bottlenecks
- Monitor disk space trends
- Track network bandwidth usage
-
Set Alerts:
- CPU usage thresholds
- Memory limits
- Disk space warnings
- Unusual network activity
-
Provide Recommendations:
- Resource optimization strategies
- Scaling recommendations
- Configuration improvements
- Performance tuning
Resource Metrics
CPU Monitoring
# Current CPU usage
top -bn1 | grep "Cpu(s)"
# Per-core usage
mpstat -P ALL 1
# Process CPU usage
ps aux --sort=-%cpu | head -10
# Load average
uptime
# Node.js CPU profiling
node --prof app.js
node --prof-process isolate-*.log
Memory Monitoring
# Memory usage
free -h
# Detailed memory info
cat /proc/meminfo
# Process memory usage
ps aux --sort=-%mem | head -10
# Memory map for specific process
pmap -x <PID>
# Node.js memory usage
node --inspect app.js
# Chrome DevTools -> Memory
Disk Monitoring
# Disk space
df -h
# Disk I/O
iostat -x 1
# Large files/directories
du -h --max-depth=1 / | sort -hr | head -20
# Disk usage by directory
ncdu /
# Monitor disk writes
iotop
Network Monitoring
# Network connections
netstat -tunapl
# Active connections
ss -s
# Bandwidth usage
iftop
# Network traffic
nload
# Connection states
netstat -ant | awk '{print $6}' | sort | uniq -c | sort -n
Monitoring Scripts
Node.js Resource Monitor
// resource-monitor.js
const os = require('os');
class ResourceMonitor {
constructor(interval = 5000) {
this.interval = interval;
this.startTime = Date.now();
}
start() {
console.log('🔍 Resource Monitor Started\n');
this.logResources();
setInterval(() => this.logResources(), this.interval);
}
logResources() {
const uptime = Math.floor((Date.now() - this.startTime) / 1000);
const cpu = this.getCPUUsage();
const memory = this.getMemoryUsage();
const load = os.loadavg();
console.clear();
console.log('📊 System Resources');
console.log('='.repeat(50));
console.log(`Uptime: ${this.formatUptime(uptime)}`);
console.log('');
console.log('CPU:');
console.log(` Usage: ${cpu.toFixed(2)}%`);
console.log(` Load Average: ${load[0].toFixed(2)}, ${load[1].toFixed(2)}, ${load[2].toFixed(2)}`);
console.log(` Cores: ${os.cpus().length}`);
console.log('');
console.log('Memory:');
console.log(` Total: ${this.formatBytes(memory.total)}`);
console.log(` Used: ${this.formatBytes(memory.used)} (${memory.percentage.toFixed(2)}%)`);
console.log(` Free: ${this.formatBytes(memory.free)}`);
this.printProgressBar('Memory', memory.percentage);
console.log('');
const processMemory = process.memoryUsage();
console.log('Process Memory:');
console.log(` RSS: ${this.formatBytes(processMemory.rss)}`);
console.log(` Heap Total: ${this.formatBytes(processMemory.heapTotal)}`);
console.log(` Heap Used: ${this.formatBytes(processMemory.heapUsed)}`);
console.log(` External: ${this.formatBytes(processMemory.external)}`);
console.log('');
this.checkThresholds(cpu, memory);
}
getCPUUsage() {
const cpus = os.cpus();
let totalIdle = 0;
let totalTick = 0;
cpus.forEach(cpu => {
for (const type in cpu.times) {
totalTick += cpu.times[type];
}
totalIdle += cpu.times.idle;
});
const idle = totalIdle / cpus.length;
const total = totalTick / cpus.length;
const usage = 100 - ~~(100 * idle / total);
return usage;
}
getMemoryUsage() {
const total = os.totalmem();
const free = os.freemem();
const used = total - free;
const percentage = (used / total) * 100;
return { total, free, used, percentage };
}
formatBytes(bytes) {
const units = ['B', 'KB', 'MB', 'GB', 'TB'];
let size = bytes;
let unitIndex = 0;
while (size >= 1024 && unitIndex < units.length - 1) {
size /= 1024;
unitIndex++;
}
return `${size.toFixed(2)} ${units[unitIndex]}`;
}
formatUptime(seconds) {
const hours = Math.floor(seconds / 3600);
const minutes = Math.floor((seconds % 3600) / 60);
const secs = seconds % 60;
return `${hours}h ${minutes}m ${secs}s`;
}
printProgressBar(label, percentage) {
const width = 40;
const filled = Math.floor(width * percentage / 100);
const empty = width - filled;
const bar = '█'.repeat(filled) + '░'.repeat(empty);
let color = '\x1b[32m'; // Green
if (percentage > 70) color = '\x1b[33m'; // Yellow
if (percentage > 85) color = '\x1b[31m'; // Red
console.log(` ${color}[${bar}] ${percentage.toFixed(1)}%\x1b[0m`);
}
checkThresholds(cpu, memory) {
const warnings = [];
if (cpu > 80) {
warnings.push(`⚠️ High CPU usage: ${cpu.toFixed(2)}%`);
}
if (memory.percentage > 80) {
warnings.push(`⚠️ High memory usage: ${memory.percentage.toFixed(2)}%`);
}
if (warnings.length > 0) {
console.log('\nWarnings:');
warnings.forEach(w => console.log(` ${w}`));
}
}
}
// Start monitoring
const monitor = new ResourceMonitor(5000);
monitor.start();
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.
- 4d ago First seen · 621 lines · 20 tokens per session scan A d3ceb1f6ef6a
resource-monitor is a skill published in the GitHub repository CuriousLearner/devkit (27 stars, last pushed 10mo ago), licensed MIT. It adds 20 tokens to every session and 3,980 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…