A skill for controlling a DG Claw assistant service managed by systemd, the Linux service manager. It can discover installed assistants and show their status or logs, restart them, start or stop them, and disable them at boot.

Checking whether a DG Claw assistant is running, reading recent logs, restarting it after configuration changes, and starting, stopping, or disabling its system service.

It turns common service operations into a defined workflow and helps interpret problems such as restart loops or a Telegram bot that does not respond.

service — Skill for Claude Code by DGatoM/DG-Claw

Install

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.

Any agent

npx skills add DGatoM/DG-Claw --skill service

Clone the repo

git clone --depth 1 https://github.com/DGatoM/DG-Claw

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dgatom/dg-claw/service/github.svg)](https://agentmods.dev/skills/dgatom/dg-claw/service)

Your own site

<a href="https://agentmods.dev/skills/dgatom/dg-claw/service"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/service/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dgatom/dg-claw/service"><img src="https://agentmods.dev/badge/skills/dgatom/dg-claw/service.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 502 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00070	$0.00502
Opus 5.5	$0.00028	$0.00201
Sonnet 5.5	$0.00014	$0.00100
Haiku 4.5	$0.00007	$0.00050

Measured 19d ago against content hash 35f672d460e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

service scanned grade B 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 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo systemctl restart "dgclaw-$SLUG"

skills/service/SKILL.md · 54 lines

What it actually says

/dgclaw:service — Controle do servico do assistente

Gerencia o servico systemd dgclaw-<slug> de um assistente DG Claw.

Descobrir os assistentes instalados

systemctl list-units --type=service --all 'dgclaw-*' --no-pager
ls -d "$HOME"/dgclaw/*/ 2>/dev/null

Se houver mais de um, pergunte qual (SLUG). Se houver so um, use ele.

Acoes

Pergunte (ou infira do pedido) o que a pessoa quer e rode:

SLUG=ana    # ajuste

# status
systemctl status "dgclaw-$SLUG" --no-pager | head -20

# logs ao vivo (ultimas linhas)
journalctl -u "dgclaw-$SLUG" --no-pager -n 50

# reiniciar (use depois de editar AGENT.md / CLAUDE.md)
sudo systemctl restart "dgclaw-$SLUG"

# desligar / ligar
sudo systemctl stop "dgclaw-$SLUG"
sudo systemctl start "dgclaw-$SLUG"

# desabilitar de vez (nao sobe mais no boot)
sudo systemctl disable --now "dgclaw-$SLUG"

Interpretar problemas comuns

active (running) = no ar.
Reiniciando em loop (Restart=always) geralmente e: token do Telegram errado, bun fora do PATH, ou workspace inexistente. Cheque journalctl e o <workspace>/.dgclaw/config.sh.
"nao responde no Telegram" mas servico ativo: confira o access.json (o ID da pessoa precisa estar em allowFrom) e se o token bate com o bot certo.

Explique o que achou em linguagem simples e proponha o conserto antes de aplicar.

Changes

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 Changed 35f672d460e6
2mo ago First seen · 54 lines · 70 tokens per session scan B c56e68888696

Subscribe to this mod's changes

service is a skill published in the GitHub repository DGatoM/DG-Claw (20 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 502 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

DevOps and cloud

service next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
serviceDGatoM/DG-Claw	Skill	20	2d ago	MIT	B	70	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

service