performance

performance is a skill for Claude Code, Codex from int2t05/engineering-skills. It costs 60 tokens per session (1,500 once invoked), scanned A, original, MIT.

A workflow for making software run faster by measuring first, finding the actual bottleneck and then checking the result. It uses profiling and performance measurements rather than guesswork.

In plain words
What is it for?
Investigating slow websites, performance regressions, response-time requirements, large datasets and high-traffic workloads.
Why use it?
It helps avoid adding complexity for a problem that is not real or is not the main cause of slowness. Before-and-after measurements show whether an optimization helped.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the engineering-skills plugin — 47 skills, 1 agent, 1 hook shipped together

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/int2t05/engineering-skills/performance
Any agent
npx skills add int2t05/engineering-skills --skill performance
Clone the repo
git clone --depth 1 https://github.com/int2t05/engineering-skills

Made for: Claude Code, Codex.

Or install engineering-skills, the plugin that ships this one along with the rest of its 47 skills, 1 agent, 1 hook.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/int2t05/engineering-skills/performance.svg)](https://agentmods.dev/skills/int2t05/engineering-skills/performance)
Your own site
<a href="https://agentmods.dev/skills/int2t05/engineering-skills/performance"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/performance.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,500 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 $0.00060 $0.01500
Opus 5 $0.00030 $0.00750
Sonnet 5 $0.00012 $0.00300
Haiku 4.5 $0.00006 $0.00150

Measured 3d ago against content hash ae18130fbcd3, 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 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.

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.

skills/05-tune/performance/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Optimization

Measure before optimizing. Performance work without measurement is guessing — and guessing leads to premature optimization that adds complexity without improving what matters. Profile first, identify the actual bottleneck, fix it, measure again. Optimize only what measurements prove matters.

When to use

  • Performance requirements exist in the spec (load time budgets, response time SLAs)
  • Users or monitoring report slow behavior, or Core Web Vitals are below thresholds
  • You suspect a change introduced a regression
  • Building features that handle large datasets or high traffic
  • Triggers on "webperf", "performance regression", "慢", "性能优化"

Not for: Don't optimize before you have evidence of a problem. Premature optimization adds complexity that costs more than the performance it gains. Diagnosing a bug (use debugging).

Steps

1. Measure — establish a baseline with real data

Two complementary approaches — use both:

  • Synthetic (Lighthouse, DevTools Performance tab): controlled, reproducible. Best for CI regression detection and isolating specific issues.
  • RUM (web-vitals library, CrUX): real user data in real conditions. Required to validate that a fix actually improved user experience.

Use the same command, same conditions, same fixed budget (wall-clock, sample count, or request count) every time. A baseline taken on a cold cache against a result taken on a warm one measures the cache, not your change.

2. Identify the actual bottleneck (not assumed)

Profile before proposing a fix. Let the symptom tell you where to look — the symptom→cause decision tree and per-category investigation tables (frontend LCP/CLS/INP, backend N+1/memory/CPU/latency) are in references/bottlenecks.md. Core Web Vitals "Good" thresholds (LCP ≤ 2.5s, INP ≤ 200ms, CLS ≤ 0.1) and performance budgets are there too.

3. Fix the specific bottleneck

Address what measurements proved matters. Common anti-patterns and their fixes — N+1 queries, unbounded data fetching, missing image optimization, unnecessary re-renders, large bundle size, missing caching — are cataloged with code in references/anti-patterns.md.

Read the full file on GitHub · 88 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 88 lines · 0 tokens per session scan A ae18130fbcd3

Subscribe to this mod's changes

performance is a skill published in the GitHub repository int2t05/engineering-skills (3 stars, last pushed 15d ago), licensed MIT. It adds 60 tokens to every session and 1,500 once invoked, about $0.0003 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.