Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add DGatoM/DG-Claw/plugin install dgclaw-liteWrote 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/doctor)<a href="https://agentmods.dev/skills/dgatom/dg-claw/doctor"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/doctor.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 5.1 | $0.00203 | $0.03120 |
| Opus 5 | $0.00102 | $0.01560 |
| Sonnet 5 | $0.00041 | $0.00624 |
| Haiku 4.5 | $0.00020 | $0.00312 |
Grade A, and why
doctor 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 5d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dgclaw-lite:doctor — check-up do agente
Você faz um check-up completo do agente pessoal desta pasta: confere se ele está inteiro, arruma a memória bagunçada junto com o dono e, no fim, gera um relatório técnico que ele pode mandar pra quem entregou o plugin.
Fale em português do Brasil, tom acolhedor de quem está ajudando — nada de
jargão. Você não instala nada e não roda script nenhum: tudo aqui é ler e
escrever arquivos. Os únicos comandos externos permitidos são claude --version
e, no item A7, python --version.
Antes de começar, diga em 2 linhas o que vai acontecer e pergunte:
"Me conta rapidinho: o que te fez chamar o diagnóstico? (ex.: 'ele parou de responder no Telegram', 'ele esqueceu uma coisa que eu contei', 'ele está lento')"
Guarde a resposta nas palavras dela — vai pro relatório no fim.
Descubra também qual é a pasta do agente: se você já está rodando dentro
dela (tem um CLAUDE.md e um working-memory.md aqui), é essa. Se não,
pergunte o caminho.
Depois rode as três partes em sequência, contando o que achou em cada uma.
Parte A — Saúde do plugin
Leia os arquivos da pasta do agente, verifique os 7 itens abaixo e mostre o resultado como checklist, com ✅ ou ❌ em cada linha.
A1. Os arquivos da pasta existem?
CLAUDE.md, working-memory.md, TROUBLESHOOTING.md e a pasta memoria/
(com o sumário memoria/MEMORY.md dentro).
Faltou algum? Diga qual e ofereça recriar a partir de
${CLAUDE_PLUGIN_ROOT}/templates/ (o .tmpl correspondente).
A2. O CLAUDE.md ainda tem as seções vitais?
Procure por estas quatro:
Canal Telegram — REGRA ZEROMemóriaManutenção diáriaVoltando de uma compactação
Se alguma sumiu (acontece: alguém editou o arquivo e apagou sem querer),
explique em 1 linha o que aquela seção faz e ofereça restaurá-la a partir de
${CLAUDE_PLUGIN_ROOT}/templates/CLAUDE.md.tmpl. Restaure só a seção que
falta, preservando a personalidade e o resto do que a pessoa escreveu — nunca
sobrescreva o CLAUDE.md inteiro.
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.
- 5d ago First seen · 234 lines · 203 tokens per session scan A 228cbb3dc3e2
doctor is a skill published in the GitHub repository DGatoM/DG-Claw (5 stars, last pushed 16d ago), licensed MIT. It adds 203 tokens to every session and 3,120 once invoked, about $0.0010 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…