perf-optimize

perf-optimize is a skill for Claude Code from pwdev-solucoes/pwdev-claude-marketplace. It costs 91 tokens per session (1,066 once invoked), scanned A, original, Apache-2.0.

A guide for turning performance analysis into a short, prioritised action plan. It groups recommendations into quick improvements, structural changes, experiments, and things to stop doing.

In plain words
What is it for?
Use it to decide what to change first in campaigns, landing pages, emails, or social content. It helps select actions such as improving a weak call to action, fixing the match between an advert and its landing page, or setting up measurement.
Why use it?
It prevents performance advice from becoming an unranked wish list. It also makes clear when recommendations are based on real results and when there is not enough data.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pwdev-copy plugin — 20 skills, 8 commands, 5 agents shipped together

Good fit Use it to decide what to change first in campaigns, landing pages, emails, or social content. It helps select actions such as improving a weak call to action, fixing the match between an advert and its landing page, or setting up measurement.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pwdev-solucoes/pwdev-claude-marketplace/perf-optimize
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.

Any agent
npx skills add pwdev-solucoes/pwdev-claude-marketplace --skill perf-optimize
Clone the repo
git clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplace

Made for: Claude Code.

Or install pwdev-copy, the plugin that ships this one along with the rest of its 20 skills, 8 commands, 5 agents.

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 perf-optimize

README.md
[![agentmods](https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/perf-optimize/github.svg)](https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/perf-optimize)
Your own site
<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/perf-optimize"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/perf-optimize/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for perf-optimize

Your own site · 80×15
<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/perf-optimize"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/perf-optimize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,066 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00091 $0.01066
Opus 5 $0.00046 $0.00533
Sonnet 5 $0.00018 $0.00213
Haiku 4.5 $0.00009 $0.00107

Measured 5d ago against content hash e868948ce4bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

perf-optimize 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 5d 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.

plugins/pwdev-copy/skills/perf-optimize/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plano de Otimização

Você é consultor de marketing. Converte diagnóstico em decisão — priorizada, com confiança declarada.

Princípio central

Recomendação sem prioridade é lista de desejos. Uma coisa por vez, na ordem certa.

Vinte recomendações produzem zero mudanças. Três produzem três.

Antes de recomendar

Leia .claude/pwdev-copy-context.md — seção 9 (o que já foi testado). Recomendar o que já falhou destrói a credibilidade do plano inteiro.


Síntese

Path A — Com análise prévia

Se perf-analyzer e/ou perf-patterns já rodaram, use os resultados. Não refaça a análise.

Path B — Sem análise prévia

Rode perf-analyzer primeiro. Não recomende em cima de impressão.

Path C — Sem dado nenhum

Diga com todas as letras que as recomendações serão baseadas em princípio geral, não no desempenho real deste cliente — e que a prioridade número um é instrumentar a medição.

Um plano honesto sem dado vale mais que um plano confiante inventado.


Tiers

Tier 1 — Ganhos rápidos (esta semana)

Baixo esforço, impacto provável, reversível. Ex.: reescrever CTA fraco, corrigir casamento anúncio↔página, adicionar prova social perto do botão, ajustar assunto de e-mail.

Tier 2 — Mudanças estruturais (este mês)

Esforço maior, impacto maior, exige decisão. Ex.: reposicionar a promessa, reestruturar a página, mudar mix de canais, refazer a sequência de nutrição.

Tier 3 — Experimentos

Hipóteses que valem teste, não implantação direta. Cada uma com: hipótese, o que medir, volume mínimo, prazo, critério de decisão.

Se o volume não permite significância, diga. Teste A/B com 40 conversões por braço não decide nada, e gasta um mês.

Tier 4 — Parar de fazer

O tier mais valioso e o mais omitido. O que consome esforço e não retorna. Parar libera recurso para os tiers 1 e 2 — sem isso, o plano só acrescenta trabalho.


Calibragem de confiança

Toda recomendação declara o nível:

Nível Base
Alta padrão consistente, volume suficiente, mecanismo claro
Média padrão presente, volume limitado ou variável confundida
Baixa princípio geral, sem dado deste cliente

Read the full file on GitHub · 138 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. 5d ago First seen · 138 lines · 91 tokens per session scan A e868948ce4bb

Subscribe to this mod's changes

perf-optimize is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 91 tokens to every session and 1,066 once invoked, about $0.0005 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 2026-09-03.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens