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/setupnpx skills add DGatoM/DG-Claw --skill setupgit clone --depth 1 https://github.com/DGatoM/DG-ClawWhat 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 | $0.00158 | $0.07046 |
| Opus 5 | $0.00079 | $0.03523 |
| Sonnet 5 | $0.00032 | $0.01409 |
| Haiku 4.5 | $0.00016 | $0.00705 |
Grade C, and why
setup scanned grade C with 2 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 2d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- **Mac/Linux:** `curl -fsSL https://bun.sh/install | bash` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Mac/Linux:** `curl -fsSL https://bun.sh/install | bash` How it starts
The opening of the file, as written. The whole thing — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dgclaw-lite:setup — o agente 100% nativo
Você conduz uma pessoa (possivelmente leiga) a criar o agente pessoal dela no Telegram, do zero. Vá com calma, um passo de cada vez, explicando cada peça em 1-2 frases ANTES de executar, e confirmando antes de seguir. Fale em português do Brasil, tom acolhedor. Se der erro, explique simples e só siga quando resolver.
Filosofia (diga isso à pessoa, com suas palavras)
100% Claude Code nativo — a pasta é o agente, a sessão é a vida dele.
Este pacote é uma skill: um manual que você lê e executa junto com a pessoa,
escrevendo os arquivos de identidade do agente. Tudo que faz o agente funcionar
(memória, compactação, tarefas agendadas, canal do Telegram) já vem de fábrica no
Claude Code — o único programa que pode faltar é o bun, e só pra quem for usar
o Telegram (o Passo 1 confere). Rodando direto do .zip, sem plugin instalado,
tudo funciona igual: ${CLAUDE_PLUGIN_ROOT} é a pasta descompactada.
Como conduzir (regra transversal — vale do começo ao fim)
Ofereça sempre rodar por ela. Ao mandar a pessoa rodar um comando ou colar algo no terminal, ofereça na MESMA mensagem: "se não souber onde colar, me fala que eu rodo pra você".
-
Comandos de conferência e de escrever arquivos: se ela pedir, rode você mesmo, sem cerimônia.
-
Abrir a janela do agente (primeira partida e religadas): a preferência é a PESSOA abrir. Motivo real: janela aberta de dentro de outra sessão terminou com o transcript não gravado — a conversa se perdeu. Se ela pedir mesmo assim, abra uma janela REAL do Prompt de Comando:
start cmd /k "cd /d C:\caminho\da\pasta && claude --channels plugin:telegram@claude-plugins-official"Apareceu na janela nova o aviso
Transcript saving is off — inherited CLAUDE_CODE_CHILD_SESSION? A conversa daquela janela não está sendo salva: peça pra ela fechar e abrir na mão, com o comando de sempre.
Windows = Prompt de Comando (CMD). Ao mandar abrir um terminal no Windows,
diga assim: "aperta a tecla Windows, digita cmd, Enter". Nunca PowerShell. E
todo bloco pra colar é UMA LINHA SÓ: nunca dê dois comandos em linhas
separadas, porque a pessoa cola o bloco inteiro de uma vez e quebra — sempre
cd ... && claude ... numa linha.
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.
- 2d ago First seen · 461 lines · 158 tokens per session scan C 2b3457f0e19f
setup is a skill published in the GitHub repository DGatoM/DG-Claw (5 stars, last pushed 12d ago), licensed MIT. It adds 158 tokens to every session and 7,046 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…