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 DGatoM/DG-Claw --skill telagit 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/tela)<a href="https://agentmods.dev/skills/dgatom/dg-claw/tela"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/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/dgatom/dg-claw/tela"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/tela.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00113 | $0.00943 |
| Opus 5.5 | $0.00045 | $0.00377 |
| Sonnet 5.5 | $0.00023 | $0.00189 |
| Haiku 4.5 | $0.00011 | $0.00094 |
Grade A, and why
tela scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s 127.0.0.1:9222/json/version How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dgclaw:tela: logins pelo dono, automação pelo Chrome logado
Eu tenho uma Tela: um Google Chrome de verdade (não headless), com perfil que guarda os logins em
~/.tela-chrome. O dono abre essa tela no painel, no botão Tela, e entra nos sistemas com o
teclado dele. Depois eu uso o mesmo Chrome, já logado, nas automações.
1. Travei num login: a senha nunca passa pela conversa
Site pediu usuário e senha, código 2FA, captcha ou confirmação de identidade? Eu paro e digo ao dono:
Abre a Tela no painel (botão Tela) e faz o login no sistema X. Me avisa quando terminar.
Regras:
- Não peço a senha, o código nem o token no chat. Nem "só dessa vez".
- Se o dono mandar a senha na conversa mesmo assim, eu não uso para digitar e não repito. Peço que faça pela Tela. Se for chave de API de um serviço, o lugar certo é o cofre do painel (aba Cofre), e eu leio a chave de lá pelo ambiente.
- Quando ele avisar que terminou, eu confiro na própria página (CDP, abaixo) se o login passou de verdade, antes de dizer que deu certo.
2. Automação: usar o Chrome já logado
Primeiro vejo se o Chrome da Tela responde:
curl -s 127.0.0.1:9222/json/version
Se vier um JSON, ele está de pé. Se não vier nada, este agente não tem Tela (ou o Chrome caiu).
Eu explico ao dono: "Este agente não tem Tela ligada. Peça a quem administra o DG Claw para
criar o agente com a imagem com navegador (ver docs/TELA-DO-AGENTE.md)." Não improviso outro
navegador para sites que exigem login.
Com o Chrome respondendo, conecto por CDP e reaproveito o contexto que já existe, que é onde estão os logins:
from playwright.sync_api import sync_playwright
with sync_playwright() as p:
browser = p.chromium.connect_over_cdp('http://127.0.0.1:9222')
contexto = browser.contexts[0] # o perfil logado, nunca um contexto novo
pagina = contexto.new_page()
try:
pagina.goto('https://sistema.exemplo.com.br/relatorios')
print(pagina.title())
finally:
pagina.close() # fecho só a página que abri
# sem browser.close(): isso derrubaria o Chrome do dono
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.
- 6d ago First seen · 73 lines · 113 tokens per session scan A 4835ae6a4047
tela is a skill published in the GitHub repository DGatoM/DG-Claw (20 stars, last pushed 2d ago), licensed MIT. It adds 113 tokens to every session and 943 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-31.
tela compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| telaDGatoM/DG-Claw | Skill | 20 | 2d ago | MIT | A | 113 | Claude Code |
| interactive-loginyc-software/qm | Skill | 16k | yesterday | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | 3d ago | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.8k | yesterday | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 895 | yesterday | MIT | A | 40 | Claude Code |