vps-prd

vps-prd is a command for Claude Code from rahmanef63/control-room. It costs 0 tokens per session (588 once invoked), scanned A, original, MIT.

A quick reference for the project's product requirements document (PRD), which describes what the software should do and how it is organised. It summarises the frontend, agent, database tables, and data collectors.

In plain words
What is it for?
Use it to check architecture, database tables, indexes, data collectors, and the rule that only the agent may access server-management tools.
Why use it?
It provides the needed project context without requiring developers to read the entire 1,400-line PRD file.

Command for Claude Code

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.

agentmods
npx agentmods add commands/rahmanef63/control-room/vps-prd
Clone the repo
git clone --depth 1 https://github.com/rahmanef63/control-room

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.

agentmods badge for vps-prd

README.md
[![agentmods](https://agentmods.dev/badge/commands/rahmanef63/control-room/vps-prd.svg)](https://agentmods.dev/commands/rahmanef63/control-room/vps-prd)
Your own site
<a href="https://agentmods.dev/commands/rahmanef63/control-room/vps-prd"><img src="https://agentmods.dev/badge/commands/rahmanef63/control-room/vps-prd.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 588 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00588
Opus 5 $0.00000 $0.00294
Sonnet 5 $0.00000 $0.00118
Haiku 4.5 $0.00000 $0.00059

Measured 4d ago against content hash 4c523e725776, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vps-prd 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 4d 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.

.claude/commands/vps-prd.md · 44 lines

What it actually says

VPS Control Room — PRD Quick Reference

Gunakan skill ini untuk mendapatkan konteks PRD tanpa membaca seluruh file 1400 baris. Jika butuh detail spesifik, baca section yang relevan dari PRD.md.

Ringkasan Arsitektur

Tiga komponen: frontend/ (Next.js 15), agent/ (Node.js host process), convex/ (self-hosted realtime DB). Agent adalah satu-satunya yang boleh akses Docker, systemd, journalctl, fail2ban, ufw.

7 Convex Tables

  1. events — timeline live, TTL 30 hari. Index: by_timestamp, by_type, by_severity.
  2. audit_log — jejak permanen. Index: by_timestamp, by_target, by_action.
  3. agent_status — upsert known agents. Index: by_name, by_status.
  4. system_snapshot — host metrics, TTL 7 hari. Index: by_timestamp.
  5. alerts — active/resolved. Index: by_status, by_severity.
  6. commands — command queue. Index: by_status, by_request_id.
  7. app_status — cache apps. Index: by_name, by_source, by_runtime_status.

5 Collectors (di agent/)

  1. system — /proc/stat, /proc/meminfo, /proc/uptime, /proc/loadavg, /proc/net/dev, df
  2. docker — Docker socket HTTP, containers, state, health, ports
  3. dokploy — Dokploy API, app list, deploy info (fallback ke docker)
  4. agents — ps aux, filter known list (openclaw-gateway, openclaw-nodes, codex, convex_realtime_daemon.py, ollama serve)
  5. security — journalctl ssh, fail2ban-client, ufw, ss -tulpn

Allowlist Actions v1

  • container.restart, container.stop, container.logs
  • service.restart (known services only)
  • dokploy.redeploy
  • fail2ban.unban

6 Dashboard Pages

Overview, Apps, Agents, Security, Events, Audit — plus Actions page dan Login.

Phase Order

0: Repo foundation → 1: Frontend shell → 2: Convex core (paralel dgn 1) → 3: Agent collectors (butuh 2) → 4: UI binding (butuh 1+2) → 5: Action pipeline (butuh 3) → 6: Hardening → 7: Deploy → 8: Verify.

Untuk detail lengkap baca: PRD.md section yang relevan.

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. 4d ago First seen · 44 lines · 0 tokens per session scan A 4c523e725776

Subscribe to this mod's changes

vps-prd is a command published in the GitHub repository rahmanef63/control-room (19 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 588 tokens. 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.