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 focogit 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/foco)<a href="https://agentmods.dev/skills/dgatom/dg-claw/foco"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/foco/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/foco"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/foco.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 | $0.00000 | $0.01357 |
| Opus 5.5 | $0.00000 | $0.00543 |
| Sonnet 5.5 | $0.00000 | $0.00271 |
| Haiku 4.5 | $0.00000 | $0.00136 |
Grade A, and why
foco 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 19d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dgclaw:foco: a lista do que importa agora
O Modo foco é uma lista curta, sua e do dono: você monta, ele tica na tela. Cada agente tem a própria lista. Ela aparece sozinha ao lado da conversa (no celular, numa faixa no topo).
Quando montar
- O dono pediu o foco do dia, "o que eu preciso fazer agora" ou ajuda para priorizar.
- A conversa terminou com um monte de pendências e ele precisa de um próximo passo claro.
Não monte por conta própria sem ele ter pedido ou aceitado a ideia. Montar avisa o celular dele.
Como montar bem
- De 3 a 7 itens. Mais que isso deixa de ser foco. O máximo do sistema é 50 itens, e o texto de cada um vai de 1 a 300 caracteres (o título, até 80).
- Verbo no começo, no infinitivo, e o item cabe numa ação só: "Revisar o contrato da Vitória", "Ligar pro Fernando", "Mandar a proposta pra Carla".
- Na ordem em que ele deve fazer. O que destrava os outros vem primeiro.
- Use as palavras do dono, os nomes que ele usa.
Os comandos
Use sempre o alias eu no lugar do seu id: só você mexe na sua lista.
# montar ou substituir a lista inteira (itens: texto puro ou {"texto", "feito"?})
dgclaw-api PUT /api/v1/foco/eu \
'{"titulo": "Foco de hoje", "itens": ["Revisar o contrato da Vitória", "Ligar pro Fernando", {"texto": "Pagar o boleto", "feito": true}]}'
# acrescentar um item no fim
dgclaw-api POST /api/v1/foco/eu/itens '{"texto": "Mandar a proposta pra Carla"}'
# ticar, desticar ou corrigir o texto (o id vem da lista)
dgclaw-api PATCH /api/v1/foco/eu/itens/42 '{"feito": true}'
# apagar um item, ou limpar a lista toda
dgclaw-api DELETE /api/v1/foco/eu/itens/42
dgclaw-api DELETE /api/v1/foco/eu
# ver a lista
dgclaw-api GET /api/v1/foco/eu
- O PUT troca a lista inteira. Sem
titulo, mantém o que ela já tinha. Para mexer em um item só, use POST, PATCH ou DELETE. "mudou": falsena resposta quer dizer que já estava assim. Nada de errado.- Quando o dono disser "já fiz X", ticar é com você (PATCH com
"feito": true) se ele não ticou sozinho.
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.
- 19d ago First seen · 102 lines · 0 tokens per session scan A 2eb63e0cccb6
foco is a skill published in the GitHub repository DGatoM/DG-Claw (20 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,357 tokens. 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 2026-10-18.
foco compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| focoDGatoM/DG-Claw | Skill | 20 | 2d ago | MIT | A | 0 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |