control-room: Agent for Claude Code

.codex/agents/vps.md

vps is an agent for Claude Code, Codex from rahmanef63/control-room. It costs 35 tokens per session (321 once invoked), scanned A, original, MIT.

An orchestration guide for a VPS Control Room project, which is a tool for managing servers and deployments from one project. It documents the project structure, build commands, environment variables, and deployment process.

In plain words
What is it for?
Use it to build the frontend and agent, run the production deployment script, check required environment variables, and delegate deployment work to the listed coding agent.
Why use it?
It gives an agent the project-specific information needed to build and deploy the application without searching through the repository. It also records an important runtime detail: the daemon must use Node.js 22 rather than Bun.

Agent for Claude CodeCodex

Written for Codex and Claude Code: installed under .codex/, but also a Claude Code subagent (agents/*.md). Also seen: mentions CLAUDE.md; mentions Codex.

This is rahmanef63/control-room's own configuration. It tells Claude Code and Codex how to work on control-room itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything control-room configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rahmanef63/control-room. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rahmanef63/control-room/main/.codex/agents/vps.md
Clone the repo
git clone --depth 1 https://github.com/rahmanef63/control-room

Made for: Claude Code, Codex.

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.

agentmods badge for vps

README.md
[![agentmods](https://agentmods.dev/badge/agents/rahmanef63/control-room/vps/github.svg)](https://agentmods.dev/agents/rahmanef63/control-room/vps)
Your own site
<a href="https://agentmods.dev/agents/rahmanef63/control-room/vps"><img src="https://agentmods.dev/badge/agents/rahmanef63/control-room/vps/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.

agentmods 80×15 button for vps

Your own site · 80×15
<a href="https://agentmods.dev/agents/rahmanef63/control-room/vps"><img src="https://agentmods.dev/badge/agents/rahmanef63/control-room/vps.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 321 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00321
Opus 5.5 $0.00014 $0.00128
Sonnet 5.5 $0.00007 $0.00064
Haiku 4.5 $0.00003 $0.00032

Measured 2mo ago against content hash 3a41e08a98d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vps 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 2mo 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.

.codex/agents/vps.md · 41 lines

What it actually says

VPS Control Room — Codex Orchestrator

Read root CLAUDE.md first. It is the architecture and execution SSOT.

Project layout

frontend/   SvelteKit 2 + Svelte 5 runes + Tailwind 4; adapter-node; Node 22 in production, Bun tooling
agent/      TypeScript/Node 22 host agent; node-pty + bounded terminal-support host APIs
packages/   shared contracts/runtime configuration
scripts/    Svelte-native deploy, systemd, local tooling

Gates

bun run docs:check
bun run --cwd frontend check
bun run --cwd frontend test
bun run --cwd frontend build
bun run --cwd agent test:all
bun run --cwd agent build
git diff --check

Runtime boundary

Browser terminal output is SSE from SvelteKit. The SvelteKit server owns the WebSocket client to the agent. The agent remains Node 22 and is the only component allowed to access PTYs/host resources.

Deploy

Use scripts/deploy.sh. For an explicitly local worktree deploy, use DEPLOY_FROM_WORKTREE=1; do not change GitHub state unless the user explicitly asks.

Prefer bounded edits and verification over broad rewrites. Distinguish local gates from GitHub CI status.

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.

  1. 2mo ago Changed · -8 lines · -1 tokens per session 3a41e08a98d1
  2. 2mo ago First seen · 49 lines · 36 tokens per session scan A e5e70d324631

Subscribe to this mod's changes

vps is an agent published in the GitHub repository rahmanef63/control-room (19 stars, last pushed 9d ago), licensed MIT. It adds 35 tokens to every session and 321 once invoked, about $0.0001 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 2026-08-30.

Related

vps compared with agents from other repositories

vps next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
vpsrahmanef63/control-roomAgent199d agoMITA35Claude Code, Codex
infrastructure-developerFortiumPartners/ensembleAgent12yesterdayMITA30Claude Code
infrastructure-specialistFortiumPartners/ensembleAgent12yesterdayMITA43Claude Code
infrastructure-orchestratorFortiumPartners/ensembleAgent12yesterdayMITA26Claude Code
devops-engineerkrivoox/agent-stack-templateAgent301mo agoMITA47Claude Code, Cursor
docs-managerdatabayt/hogwartsAgent183d agononeA10Claude Code
ui-factorydatabayt/hogwartsAgent183d agononeA18Claude Code