What is ag-testar-manual?

A manual browser-testing helper that explores an application through Playwright instead of reading its code. It can capture screenshots, browser-console problems, and accessibility issues.

Use it to browse an application as a person would, inspect pages and interactions, and report visible, console, or accessibility problems.

It helps reveal visual and interaction problems that scripted checks or code inspection may miss, especially before merging or deploying changes.

ag-testar-manual — Skill for Claude Code by andregusman-raiz

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 andregusman-raiz/a-gusman-claude --skill ag-testar-manual

Clone the repo

git clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claude

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-testar-manual/github.svg)](https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-testar-manual)

Your own site

<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-testar-manual"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-testar-manual/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-testar-manual"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-testar-manual.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,096 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 4
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00038	$0.02096
Opus 5	$0.00019	$0.01048
Sonnet 5	$0.00008	$0.00419
Haiku 4.5	$0.00004	$0.00210

Measured 9d ago against content hash f9f098a1a2d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ag-testar-manual 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 9d 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/ag-testar-manual/SKILL.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ferramentas

Playwright MCP (preferido): Plugin MCP @playwright/mcp — browser automation nativo
Playwright CLI (fallback): /opt/homebrew/bin/playwright-cli

ag-testar-manual — Testar Manual via Playwright MCP

Papel

O QA Exploratorio: usa Playwright MCP (ou CLI como fallback) para controlar um browser real e testar a aplicacao como um usuario humano faria. NAO le codigo — so interage pelo browser.

Diferenca de ag-testar-e2e: ag-testar-e2e escreve e roda scripts Playwright. ag-testar-manual navega manualmente e reporta. Diferenca de ag-capturar-tela: ag-capturar-tela captura TELA INTEIRA (apps nativos, desktop). ag-testar-manual interage com BROWSER.

Fallback para apps nativos

Se o alvo nao e um browser (app desktop, IDE, terminal), usar ag-capturar-tela como fallback:

Agent({ subagent_type: "ag-capturar-tela", prompt: "Capture a tela e descreva o app nativo visivel" })

Estrategia de Ferramentas

Preferir MCP tools do plugin Playwright quando disponivel (mais integrado, sem Bash intermediario)
Fallback para playwright-cli via Bash se MCP nao estiver ativo na sessao
Verificar disponibilidade: se MCP tools de browser estao no contexto → usar MCP

Referencia de comandos

Navegacao e interacao

playwright-cli open [url]              # Abrir browser
playwright-cli goto <url>              # Navegar para URL
playwright-cli snapshot                # Capturar estado (obter refs)
playwright-cli click <ref>             # Clicar elemento
playwright-cli fill <ref> <text>       # Preencher campo
playwright-cli type <text>             # Digitar texto
playwright-cli select <ref> <val>      # Selecionar dropdown
playwright-cli check <ref>             # Marcar checkbox
playwright-cli uncheck <ref>           # Desmarcar checkbox
playwright-cli hover <ref>             # Hover sobre elemento
playwright-cli dblclick <ref>          # Duplo clique
playwright-cli press <key>             # Pressionar tecla

Captura e evidencias

playwright-cli screenshot [ref]        # Screenshot da pagina ou elemento
playwright-cli pdf                     # Salvar como PDF
playwright-cli snapshot                # Estado textual da pagina

Read the full file on GitHub · 221 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.

9d ago First seen · 221 lines · 38 tokens per session scan A f9f098a1a2d1

Subscribe to this mod's changes

ag-testar-manual is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 2,096 once invoked, about $0.0002 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.

Browser automation Claude Code E2E testing Testing ai-agents automation developer-tools

ui-test

Runs UI tests described in plain English by driving real Chrome via the Claude-in-Chrome extension. Covers end-to-end flows (clicks, forms, assertions), visual checks (screenshot + optional baseline diff), accessibility (axe-core), performance (Web Vitals + light Lighthouse-style metrics), and an interactive --debug…

mostafa-drz/claude-skills · 190 tokens

audit-ui-e2e

Runs a beginner-mind end-to-end UI audit of any running app — local dev server, staging, production, or a specific URL. Drives Chrome through every interactive element on the target surface, collects structured findings (severity, category, where, symptom, impact, repro, triage), and hands the result off to…

mostafa-drz/claude-skills · 152 tokens

capture-screens

Automatically navigates a web app using Playwright MCP and captures context-aware named screenshots at each product feature state. Names each file semantically based on context (e.g., checkout-payment-form-filled.png). Outputs a manifest.json mapping filenames to descriptions and a summary report. Use when documenting…

mostafa-drz/claude-skills · 101 tokens

browse

Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. 100ms per command. Use when you need to test a…

Ertinox7711/SGRR-AGI-V2 · 119 tokens

test-browser

Run browser tests on pages affected by current PR or branch.

gvkhosla/compound-engineering-pi · 14 tokens

verify

Drive the Vite desktop SPA to verify AppShell / Workbench sidebar changes.

mmletgo/cc-partner · 17 tokens