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.
npx skills add andregusman-raiz/a-gusman-claude --skill ag-testar-manualgit clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claudeWrote 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.
[](https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-testar-manual)<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.
<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>- NVIDIA SkillSpector warn
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.
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 5.5 | $0.00015 | $0.00838 |
| Sonnet 5.5 | $0.00008 | $0.00419 |
| Haiku 4.5 | $0.00004 | $0.00210 |
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 1mo 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.
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-clivia 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
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.
- 1mo ago First seen · 221 lines · 38 tokens per session scan A f9f098a1a2d1
ag-testar-manual is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (18 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 2,096 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…