What is deploy-sentinel?

Deployment instructions for Claude Sentinel, a persistent Telegram gateway that keeps Claude sessions running on a VPS, a rented remote server.

For installing the Telegram gateway, creating systemd services and cron jobs, configuring memory compaction, and checking deployment health.

It turns the required services, scheduled maintenance, configuration, and bot identity into a checked deployment process.

deploy-sentinel — Skill for Claude Code by southlab-ai

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 southlab-ai/Claude-Plugin-Marketplace --skill deploy-sentinel

Clone the repo

git clone --depth 1 https://github.com/southlab-ai/Claude-Plugin-Marketplace

Made for: Claude Code.

Or install claude-sentinel, the plugin that ships this one along with the rest of its 4 skills.

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/southlab-ai/claude-plugin-marketplace/deploy-sentinel/github.svg)](https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/deploy-sentinel)

Your own site

<a href="https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/deploy-sentinel"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/deploy-sentinel/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/southlab-ai/claude-plugin-marketplace/deploy-sentinel"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/deploy-sentinel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,506 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 2 findings. 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	$0.00102	$0.02506
Opus 5	$0.00051	$0.01253
Sonnet 5	$0.00020	$0.00501
Haiku 4.5	$0.00010	$0.00251

Measured 11d ago against content hash 6fc7f858d9bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

deploy-sentinel scanned grade B 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 11d 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.

chmod 600 ~/.claude/channels/telegram/.env

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Bash(curl *)

plugins/claude-sentinel/skills/deploy-sentinel/SKILL.md · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sentinel:deploy — Deploy Claude Sentinel

Installs the Claude Sentinel persistent gateway on the current machine. Creates all required directories, configuration files, systemd services, cron jobs, and bot identity.

Prerequisites (verify before proceeding):

Claude Code CLI installed and authenticated (claude auth status → loggedIn: true)
Bun runtime installed (bun --version)
Running as a non-root user (not root)
Telegram bot token available (from @BotFather)
User lingering enabled (loginctl show-user $(whoami) | grep Linger)

If any prerequisite is missing, direct the user to run /sentinel:vps-setup first.

Arguments passed: $ARGUMENTS

Dispatch on arguments

No args — full guided deployment

Walk through all steps below in order. Verify each step before moving on. Ask the user for required input (tokens, bot name, etc.) when needed.

`status` — check deployment health

Check if gateway.ts exists: ls ~/.claude/channels/telegram/gateway.ts
Check service status: systemctl --user is-active telegram-gateway.service
Check timer status: systemctl --user list-timers | grep compact
Check identity: ls ~/.claude/channels/telegram/identity.md
Check compact file: ls ~/.claude/channels/telegram/session-compact.md
Check message count: sqlite3 ~/.claude/channels/telegram/history.db "SELECT COUNT(*) FROM messages"
Report overall health.

`restart` — restart the gateway

systemctl --user restart telegram-gateway.service
journalctl --user -u telegram-gateway.service --no-pager -n 10

`compact` — run memory compaction now

systemctl --user start telegram-compact.service
journalctl --user -u telegram-compact.service --no-pager -n 20

`logs` — show recent gateway logs

journalctl --user -u telegram-gateway.service --no-pager -n 30

Full deployment steps

Step 1: Create directory structure

mkdir -p ~/.claude/channels/telegram/inbox
mkdir -p ~/.claude/channels/telegram/approved
mkdir -p ~/.claude/channels/telegram/crons
mkdir -p ~/.config/systemd/user

Read the full file on GitHub · 317 lines

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.

11d ago First seen · 317 lines · 102 tokens per session scan B 6fc7f858d9bc

Subscribe to this mod's changes

deploy-sentinel is a skill published in the GitHub repository southlab-ai/Claude-Plugin-Marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 2,506 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Claude Code Cloud DevOps and cloud Multi-Agent ai-agents computer-vision marketplace mcp

vast-ai-gpu-cloud

Safely inspect and operate Vast.ai marketplace instances with the vastai CLI, live offer data, and explicit approval before paid or destructive actions.

synthetic-sciences/openscience · 34 tokens

oma-tf-infra

Infrastructure-as-code specialist for multi-cloud provisioning using Terraform across any provider (AWS, GCP, Azure, Oracle Cloud). Use for terraform plan/apply, state management, compute, databases, storage, networking, IAM, OIDC, cost optimization, policy-as-code, ISO/IEC 42001 AI controls, ISO 22301 continuity, and…

first-fluke/oh-my-agent · 87 tokens

architecture-diagram

Dark-themed SVG architecture/cloud/infra diagrams as HTML.

mateaix/mateclaw · 15 tokens

deploy-gen

Generate deployment configurations (Docker, Kubernetes) for the current project.

jmagly/aiwg · 15 tokens

cockpit-headless-deploy

Guide or repair a headless Linux AIWG Cockpit plus Agentic Sandbox deployment when host topology, SSH access, service persistence, or runtime readiness must be planned safely.

jmagly/aiwg · 41 tokens

stack-baseline

The pinned default technology stack for SMB Product-Builder products. One source of truth so the architect, app-scaffolder, auth-engineer, and senior-dev never re-decide the stack per build — they build ON it. Covers framework, ORM/DB, auth, UI, payments/email/SMS, files, jobs, testing, hosting, and observability…

avelikiy/great_cto · 126 tokens

deploy-sentinel