performance

A performance debugging assistant for finding causes of slow websites and applications, such as expensive page updates, oversized code bundles, repeated database requests, or memory leaks.

In plain words
What is it for?
Use it to inspect a page or application, identify performance problems, and guide fixes for slow loading, slow interactions, APIs, memory use, or bundle size.
Why use it?
It gives a structured way to investigate sluggish software instead of relying on guesses about what is wrong.

Command for Claude Code

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 commands/dork-labs/dorkos/performance
Clone the repo
git clone --depth 1 https://github.com/dork-labs/dorkos

Made for: Claude Code.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,922 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00019 $0.02922
Opus 5 $0.00010 $0.01461
Sonnet 5 $0.00004 $0.00584
Haiku 4.5 $0.00002 $0.00292

Measured 2d ago against content hash 118b9d78405f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance 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.

.claude/commands/debug/performance.md · 431 lines

How it starts

The opening of the file, as written. The whole thing — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Debugging

Diagnose and resolve performance issues including slow renders, large bundle sizes, N+1 database queries, memory leaks, and general sluggishness.

Arguments

Parse $ARGUMENTS:

  • If --url <url> flag provided, navigate to that URL for profiling
  • Remaining text describes the performance symptom
  • If empty, prompt for details

Phase 1: Problem Identification

Infer the symptom class (slow load / sluggish interactions / bundle size / memory / slow API / general), the scope (page, component, whole app, dev-only), and the timeline (recent regression vs always slow) from $ARGUMENTS and the initial profiling. Ask a clarifying question only when the answer genuinely changes the investigation path — a recent regression points at git log, "gets slower over time" points at leaks.

Phase 2: Initial Profiling

2.1 Browser Performance Check

If URL provided, navigate and profile:

mcp__plugin_playwright_playwright__browser_navigate: { url: "[url]" }
mcp__plugin_playwright_playwright__browser_snapshot: {}
mcp__plugin_playwright_playwright__browser_console_messages: { level: "warning" }
mcp__plugin_playwright_playwright__browser_network_requests: { includeStatic: true }

2.2 Check for Console Warnings

Look for performance-related warnings:

  • React rendering warnings
  • Memory warnings
  • Long task warnings
  • Deprecated API warnings

2.3 Network Timing Analysis

Analyze network requests for:

  • Large payloads: Responses > 100KB
  • Slow requests: Requests > 1s
  • Waterfall issues: Requests blocking each other
  • Duplicate requests: Same endpoint called multiple times

2.4 Basic Performance Metrics

mcp__plugin_playwright_playwright__browser_evaluate: {
  function: "() => { const timing = performance.timing; return { loadTime: timing.loadEventEnd - timing.navigationStart, domReady: timing.domContentLoadedEventEnd - timing.navigationStart, firstPaint: performance.getEntriesByType('paint')[0]?.startTime || 'N/A' }; }"
}

Read the full file on GitHub · 431 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 · 431 lines · 19 tokens per session scan A 118b9d78405f

Subscribe to this mod's changes

performance is a command published in the GitHub repository dork-labs/dorkos (9 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 2,922 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 2026-08-31.