cursorrules

A set of Cursor editor rules for Busibox, a local platform for running language models in Docker or Proxmox containers. It explains which approved commands agents must use for deploying and managing services.

In plain words
What is it for?
Use it when working on Busibox services, especially for installs, restarts, deployments, and other operations that require Ansible Vault credentials.
Why use it?
It helps prevent service failures caused by bypassing the project's secrets handling and deployment process.

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/jazzmind/busibox/cursorrules
Clone the repo
git clone --depth 1 https://github.com/jazzmind/busibox

Made for: Cursor.

Per session 1,896 This file is loaded in full into every session.
When invoked 1,896 The same file — it is already loaded in full.
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 $0.01896 $0.01896
Opus 5 $0.00948 $0.00948
Sonnet 5 $0.00379 $0.00379
Haiku 4.5 $0.00190 $0.00190

Measured yesterday against content hash af6e54c0e829, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 yesterday.

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.

.cursorrules · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Busibox Cursor Rules

Overview

Busibox is a local LLM infrastructure platform running on Docker or Proxmox LXC containers. See CLAUDE.md for full project documentation.

⚠️ CRITICAL: Service Operations

NEVER run docker compose, docker, or ansible-playbook commands directly.

# ❌ WRONG - bypasses secrets injection
docker compose up -d authz-api
docker restart prod-authz-api
ansible-playbook -i inventory/docker docker.yml --tags authz

# ✅ CORRECT for AI agents - use make with vault password
make install SERVICE=authz
make manage SERVICE=authz ACTION=restart

Why: Secrets are injected from Ansible Vault at runtime. Direct commands skip this and cause authentication failures.

Vault password: Most make targets require ANSIBLE_VAULT_PASSWORD env var or a vault password file (~/.busibox-vault-pass-*). If neither is available, ask the user for the vault password. Prefer mcp-admin MCP tools when available — they handle SSH and targeting.

Humans use the Busibox CLI (busibox), not make targets. The CLI handles vault decryption interactively.

Quick Reference:

  • Deploy: make install SERVICE=authz
  • Restart: make manage SERVICE=authz ACTION=restart
  • Logs: make manage SERVICE=authz ACTION=logs
  • Status: make manage SERVICE=authz ACTION=status
  • Redeploy: make manage SERVICE=authz ACTION=redeploy
  • Rebuild manager: make build-manager
  • Skip manager: make install SERVICE=authz USE_MANAGER=0

See .cursor/rules/010-make-commands.md for complete reference and docs/developers/reference/mcp-and-make-internals.md for vault password flow.

Critical: Organization Rules

ALWAYS follow these rules when creating or moving files:

Documentation Organization

Read: .cursor/rules/001-documentation-organization.md

Quick Reference (organized by audience):

  • Deployment/config/operations → docs/administrators/
  • Architecture/API guides/reference → docs/developers/
  • End-user platform guides → docs/users/
  • Historical/outdated → docs/archive/

Read the full file on GitHub · 207 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.

  1. yesterday First seen · 207 lines · 1,896 tokens per session scan A af6e54c0e829

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository jazzmind/busibox (7 stars, last pushed 4d ago), licensed MIT. It adds 1,896 tokens to every session, about $0.0095 per session on Opus 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 2026-08-31.