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 avatargit 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/avatar)<a href="https://agentmods.dev/skills/dgatom/dg-claw/avatar"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/avatar/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/avatar"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/avatar.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 | $0.00127 | $0.00688 |
| Opus 5.5 | $0.00051 | $0.00275 |
| Sonnet 5.5 | $0.00025 | $0.00138 |
| Haiku 4.5 | $0.00013 | $0.00069 |
Grade A, and why
avatar 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dgclaw:avatar: a cara do assistente no painel
O painel mostra uma figura do assistente no cabecalho. No DG Claw ela e fixa: uma so imagem, sempre a mesma, porque o nucleo nao tem estado emocional.
Se a extensao DG Alive estiver instalada, essa mesma figura passa a trocar conforme o humor (alegre, animado, pensativo, triste, irritado, cansado). E a extensao que ativa isso e que traz o mapa de humor para figura. Explique assim se o dono perguntar por que a carinha nao muda.
Os arquivos ficam em:
<workspace>/.dgclaw/panel/public/assets/sprites/
avatar.jpg rosto no cabecalho (o que o DG Claw usa)
default.gif figura parada, usada quando nao ha humor definido
Pergunte qual dos tres caminhos o dono quer:
(a) Usar o que ja vem
Nao faz nada: o painel ja vem com uma figura neutra. Bom pra ver o painel funcionando antes de investir no visual. Da pra trocar quando quiser.
(b) Gerar a partir da aparencia dele
- Use a aparencia descrita nos arquivos de identidade do agente (e a imagem de
referencia em
<ws>/assets/reference/base.jpg, se existir). - Gere um retrato com expressao neutra, mantendo o rosto da referencia. O da referencia do autor foi feito com GPT-image em estilo pixel art, mas o estilo e escolha do dono: pode ser ilustracao, foto estilizada, desenho.
- Salve como
avatar.jpg(e, se quiser a versao animada parada,default.gif) na pasta acima. - Mostre o resultado pro dono aprovar antes de fixar.
Se as ferramentas de geracao de imagem nao estiverem disponiveis nesta maquina, oriente o dono a gerar onde ele preferir e mandar o arquivo (caminho c).
(c) Subir a propria imagem
O dono manda a imagem e voce copia pra pasta acima com o nome avatar.jpg.
Ao final
systemctl restart "dgclaw-panel-<slug>.service"
Atualize tambem o campo avatar.path em <ws>/.dgclaw/agent.json e peca pra ele
recarregar a pagina. Se ele quiser a figura reagindo ao humor, e ai que entra o DG
Alive: a extensao instala o jogo completo de expressoes.
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 · 59 lines · 127 tokens per session scan A f8047eab62d8
avatar is a skill published in the GitHub repository DGatoM/DG-Claw (20 stars, last pushed 2d ago), licensed MIT. It adds 127 tokens to every session and 688 once invoked, about $0.0005 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 2026-10-18.
avatar compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| avatarDGatoM/DG-Claw | Skill | 20 | 2d ago | MIT | A | 127 | 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 |