performance-audit

performance-audit is a skill for Claude Code, Codex from ashtonian/llm-init. It costs 12 tokens per session (1,530 once invoked), scanned A, original, MIT.

A structured process for examining an application's speed and resource use through profiling and benchmarks. It covers CPU, memory, goroutines or threads, garbage collection, and frontend performance measurements.

In plain words
What is it for?
Use it to profile Go, Node.js, or browser-based applications and produce recommendations based on measured bottlenecks.
Why use it?
It helps locate the parts of an application that consume the most time or memory. Measurements provide a basis for deciding which performance problems to address.

Skill for Claude CodeCodex

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 skills/ashtonian/llm-init/performance-audit
Any agent
npx skills add ashtonian/llm-init --skill performance-audit
Clone the repo
git clone --depth 1 https://github.com/ashtonian/llm-init

Made for: Claude Code, Codex.

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/ashtonian/llm-init/performance-audit.svg)](https://agentmods.dev/skills/ashtonian/llm-init/performance-audit)
Your own site
<a href="https://agentmods.dev/skills/ashtonian/llm-init/performance-audit"><img src="https://agentmods.dev/badge/skills/ashtonian/llm-init/performance-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,530 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found 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 $0.00012 $0.01530
Opus 5 $0.00006 $0.00765
Sonnet 5 $0.00002 $0.00306
Haiku 4.5 $0.00001 $0.00153

Measured 4d ago against content hash af1393433a38, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance-audit 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:8080/debug/pprof/goroutine?debug=2
templates/.claude/skills/performance-audit/SKILL.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Audit Skill

Structured workflow for conducting a systematic performance audit of the application. Identifies bottlenecks, measures baselines, and produces actionable recommendations.

Workflow

Step 1: Profile CPU and Memory

Run profiling tools to identify hot paths and allocation sites.

Go:

# CPU profile
go test -bench=. -cpuprofile=cpu.prof -benchtime=30s ./...
go tool pprof -http=:8080 cpu.prof

# Memory profile
go test -bench=. -memprofile=mem.prof -benchmem ./...
go tool pprof -http=:8080 mem.prof

# Goroutine profile (for concurrency issues)
curl http://localhost:8080/debug/pprof/goroutine?debug=2

Node.js:

# CPU profile
node --cpu-prof --cpu-prof-dir=./profiles app.js
# Then: chrome://inspect -> Open dedicated DevTools for Node

# Memory
node --heap-prof --heap-prof-dir=./profiles app.js

Frontend (Chrome DevTools):

  • Performance tab: Record user interaction flow
  • Memory tab: Heap snapshots before/after interaction
  • Lighthouse: Overall performance score

Capture:

  • Top 10 CPU-consuming functions
  • Top 10 memory-allocating functions
  • Goroutine/thread count under load
  • GC pause times and frequency

Step 2: Identify Hot Paths and Allocation Sites

From profiling data, identify:

Category What to Find
CPU hot paths Functions consuming >5% of total CPU
Memory allocations Functions with >1000 allocs/op or >1MB/op
GC pressure Allocation rate causing frequent GC pauses
Contention Lock contention in concurrent code
I/O bottlenecks Functions blocked on network/disk I/O

For each finding, document:

  • Function name and call chain
  • Current metric (CPU%, allocs/op, bytes/op)
  • Potential optimization approach
  • Estimated improvement

Step 3: Benchmark Critical Endpoints

Use HTTP load testing tools to measure endpoint performance:

# Quick benchmark with hey
hey -n 10000 -c 50 -H "Authorization: Bearer $TOKEN" \
    http://localhost:8080/api/v1/users

# Detailed benchmark with wrk
wrk -t4 -c100 -d30s -s scripts/post-user.lua \
    http://localhost:8080/api/v1/users

# Multi-tenant load simulation with k6
k6 run --vus 100 --duration 60s scripts/multi-tenant-load.js

Read the full file on GitHub · 220 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. 4d ago First seen · 220 lines · 12 tokens per session scan A af1393433a38

Subscribe to this mod's changes

performance-audit is a skill published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 1,530 once invoked, about $0.0001 per session on Opus 5. 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens