closed-nongoals

A set of rules that records features deliberately left out of a Proxmox management integration.

In plain words
What is it for?
It helps keep gap reports and future plans focused by excluding long-lived console proxies, full Proxmox Backup Server administration, and ungated Ceph operations.
Why use it?
It prevents the coding agent from treating these excluded features as bugs, planned work, or unfinished enhancements.

Cursor rule for Cursor

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 rules/hackmods/cursor-proxmox-mcp/closed-nongoals
Clone the repo
git clone --depth 1 https://github.com/hackmods/cursor-proxmox-mcp

Made for: Cursor.

Per session 220 This file is loaded in full into every session.
When invoked 220 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin fork From a forked repository.
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 $0.00220 $0.00220
Opus 5 $0.00110 $0.00110
Sonnet 5 $0.00044 $0.00044
Haiku 4.5 $0.00022 $0.00022

Measured 2d ago against content hash b70c032c2143, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

closed-nongoals 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 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.

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.

.cursor/rules/closed-nongoals.mdc · 15 lines

What it actually says

Closed non-goals (D30)

Do not suggest, plan, or document these as missing / planned / Phase C remainder enhancements unless the user explicitly asks to reverse D30:

  1. Long-lived VNC/SPICE websocket proxy inside MCP (tickets + get_console_connection only — D6).
  2. Full PBS product admin (separate PBS API: users/remotes/sync/prune). PVE type=pbs storage + get_pbs_storage_status is the scope.
  3. Ungated Ceph OSD/MON/MGR create/destroy. Gated OSD only: list_node_diskspropose_ceph_osdcreate_ceph_osd/destroy_ceph_osd with typed confirm + dry-run default.

When summarizing gaps or next work, omit these three. See .cursor/research/decisions.md D30.

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. 2d ago First seen · 15 lines · 220 tokens per session scan A b70c032c2143

Subscribe to this mod's changes

closed-nongoals is a cursor rule published in the GitHub repository hackmods/cursor-proxmox-mcp (1 stars, last pushed 16d ago), licensed MIT. It adds 220 tokens to every session, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.