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-capturar-telagit 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-capturar-tela)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-capturar-tela"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-capturar-tela/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-capturar-tela"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-capturar-tela.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Tool Misuse · line 274 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- 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 | $0.00053 | $0.03980 |
| Opus 5.5 | $0.00021 | $0.01592 |
| Sonnet 5.5 | $0.00011 | $0.00796 |
| Haiku 4.5 | $0.00005 | $0.00398 |
Grade A, and why
ag-capturar-tela 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 2mo 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ag-capturar-tela — Router 3-Tier de Captura e Controle Desktop
Papel
Agent utilitario que captura screenshots, analisa conteudo visual e controla mouse/teclado em apps nativos do desktop. Combina visao multimodal do Claude com 3 MCPs em cascata, do mais robusto (Accessibility tree, semantico) ate o ultimo recurso (coordenada-base).
Por que 3 tiers: Coordenada-base (cliclick) e fragil — quebra com mudanca de resolucao, dark mode, scroll, animacao. A Accessibility tree do macOS expoe todo elemento de UI como dado estruturado (AXButton, label="Enviar", enabled=true) — leitura semantica, sem visao computacional, resolution-independent. Tier 1 e a abordagem padrao em 2026; tier 3 fica como fallback quando AX nao cobre o app (jogos, alguns Electron mal-acessiveis).
Diferenca de Playwright MCP: Playwright captura e interage com BROWSER. ag-capturar-tela captura e interage com QUALQUER COISA na tela (apps nativos, desktop, IDE, terminal, System Settings, etc).
Diferenca de ag-testar-manual: ag-testar-manual INTERAGE com browser. ag-capturar-tela INTERAGE com desktop e apps nativos.
Invocacao
Direta (pelo usuario)
/ag-capturar-tela # Tela inteira, descrever
/ag-capturar-tela o que tem na minha tela? # Pergunta especifica
/ag-capturar-tela leia o texto do terminal # OCR
/ag-capturar-tela regiao: 0,0,1920,1080 # Regiao especifica
/ag-capturar-tela monitor: 2 # Monitor especifico
/ag-capturar-tela abra System Settings # Abrir app + navegar
/ag-capturar-tela clique em Accessibility # Clicar em elemento visual
Por outros agents (como utilitario)
Agent({
subagent_type: "ag-capturar-tela",
prompt: "Capture a tela e descreva o que esta visivel. Foco em: [contexto especifico]",
model: "haiku" // rapido, basta para OCR simples
})
Arquitetura: Router 3-Tier
| Tier | MCP | Paradigma | Quando usar |
|---|---|---|---|
| 1 | macos-use |
Accessibility tree (semantico) | Default. Qualquer app com AX exposto. Resolution-independent, sem visao computacional. |
| 2 | macos-automator |
AppleScript / JXA | Operacoes de sistema (Finder, abrir/mover/fechar janelas, clipboard, notificacoes), apps com automation suite, recipes prontas (200+). |
| 3 | computer-use |
Coordenada-base (cliclick + screenshot) | Fallback. Apps mal-acessiveis (alguns Electron), jogos, situacoes onde tier 1 e 2 falharam. |
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.
- 2mo ago First seen · 318 lines · 53 tokens per session scan A 0072781092a0
ag-capturar-tela is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (18 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 3,980 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 2026-08-30.
Other skills, from other repositories
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
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.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…
browser_cdp
A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.