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 agentmods add skills/dgatom/dg-claw/connectnpx skills add DGatoM/DG-Claw --skill connectgit clone --depth 1 https://github.com/DGatoM/DG-ClawWrote 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/dgatom/dg-claw/connect)<a href="https://agentmods.dev/skills/dgatom/dg-claw/connect"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/connect.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00124 | $0.00868 |
| Opus 5 | $0.00062 | $0.00434 |
| Sonnet 5 | $0.00025 | $0.00174 |
| Haiku 4.5 | $0.00012 | $0.00087 |
Grade A, and why
connect 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dgclaw-lite:connect — dar ao agente acesso ao Google
Liga Google Drive, Gmail e Google Calendar no agente usando os connectors nativos do Claude Code. Não precisa criar projeto no Google Cloud, não precisa mexer em OAuth: a pessoa autoriza a própria conta Google no navegador, e pronto.
Fale em português do Brasil, tom acolhedor, um passo por mensagem.
Explique antes (2 frases, sem jargão)
"O Claude Code já vem com conexões oficiais pro Google. Você autoriza uma vez, com a sua conta, e o seu agente ganha ferramentas de verdade: ler e criar arquivos no Drive, ler e escrever e-mail no Gmail, ver e marcar compromisso na Agenda. Nada de programar nada — é só aprovar numa tela do Google."
Passos
-
Liste as conexões disponíveis nesta janela:
/mcp -
Autorize um de cada vez: procure Google Drive, Gmail e Google Calendar e siga o fluxo de autorizar/login de cada um. Abre uma página do Google pra aprovar — use a conta que o agente deve enxergar. Conecte só o que fizer sentido: dá pra ligar só a Agenda, por exemplo.
-
Confirme: rode
/mcpde novo e veja se aparecem como conectados. -
Feche a janela do agente e religue com o comando de sempre — este passo não é opcional:
cd /d "<a pasta do agente>" && claude --continue --channels plugin:telegram@claude-plugins-official(no Mac/Linux, a mesma linha sem o
/d; quem usa só o terminal roda a mesma linha sem o--channels ...). As conexões valem por sessão: a janela que já estava aberta continua sem enxergar as ferramentas novas. É só religar que ele passa a usar — a conversa não se perde.
Teste
Peça pra pessoa mandar pelo Telegram algo como:
"vê meus próximos eventos da agenda"
"resume meus últimos e-mails"
Se ele responder com dados reais, está conectado. Se ele disser que não tem essas ferramentas, quase sempre é o passo 4: a janela não foi religada.
Se não aparecer nenhum connector do Google no /mcp
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.
- 3d ago First seen · 77 lines · 124 tokens per session scan A 13788a5d4cb5
connect is a skill published in the GitHub repository DGatoM/DG-Claw (5 stars, last pushed 14d ago), licensed MIT. It adds 124 tokens to every session and 868 once invoked, about $0.0006 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.
Other skills, from other repositories
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.