agentmods.dev

pvetui AGENTS.md

Development instructions for pvetui, a terminal user interface for Proxmox, a system for managing virtual machines and containers. They cover setup, workflow, code quality, documentation, security, plugins, and testing.

In plain words
What is it for?
Use them to set up development, update the embedded noVNC client, run checks and tests, follow style and commit rules, and develop or maintain plugins.
Why use it?
They collect the project's required commands, conventions, and common problem fixes so contributors can make changes consistently.

Instructions file for CodexOpenCode

716 5d ago B scan 6,094 tokens original MIT
View the source file devnullvoid/pvetui
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 instructions/devnullvoid/pvetui/agents-md
Clone the repo
git clone --depth 1 https://github.com/devnullvoid/pvetui

Made for: Codex, OpenCode.

Per session 6,094 This file is loaded in full into every session.
When invoked 6,094 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.06094 $0.06094
Opus 5 $0.03047 $0.03047
Sonnet 5 $0.01219 $0.01219
Haiku 4.5 $0.00609 $0.00609

Measured yesterday against content hash 1bf800528a6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

pvetui AGENTS.md scanned grade B with 1 finding 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Install direnv: `sudo pacman -S direnv` or equivalent
AGENTS.md · 442 lines

How it starts

The opening of the file, as written. The whole thing — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENT INSTRUCTIONS

Last Updated: June 2026 (Cloudsmith packaging) | For: pvetui - Proxmox TUI

Table of Contents

The following conventions must be followed for any changes in this repository.

Initial Setup

  1. Run development setup: make dev-setup (installs required tools and validates environment).
  2. The embedded noVNC client lives in a git subtree; sync it with upstream when needed via make update-novnc.
  3. For enhanced development experience (optional):
    • Install direnv: sudo pacman -S direnv or equivalent
    • Copy .envrc.example to .envrc and configure as needed
    • Install pre-commit hooks: pre-commit install

Development Workflow

  1. Confirm the application builds with make build.
  2. Run comprehensive code quality checks with make code-quality (includes go vet and golangci-lint).
  3. Execute all tests with make test.
  4. For integration tests: make test-integration (requires Proxmox environment).
  5. Keep the working tree clean before finishing.

Read the full file on GitHub · 442 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 · 442 lines · 6,094 tokens per session scan B 1bf800528a6f

Subscribe to this mod's changes

pvetui AGENTS.md is an instructions file published in the GitHub repository devnullvoid/pvetui (716 stars, last pushed 5d ago), licensed MIT. It adds 6,094 tokens to every session, about $0.0305 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code reviewSecurityTestinggoproxmoxproxmox-vepveterminal-uitui
Related

Other instructions, from other repositories

FluffyUI AGENTS.md

Instructions for odvcencio/FluffyUI, covering agents.md - contribution guide for fluffyui, project overview, directory structure, architecture and message-loop architecture.

odvcencio/FluffyUI · 3,548 tokens

zot AGENTS.md

Instructions for patriceckhart/zot, covering working agreement for zot, product intent, starting a task, code ownership map and correctness contracts.

patriceckhart/zot · 1,909 tokens

go-proxmox AGENTS.md

Instructions for luthermonson/go-proxmox, covering agents.md, build, test, lint, integration test env vars, architecture and client and request layer (proxmox.go).

luthermonson/go-proxmox · 6,369 tokens

waveloom AGENTS.md

Instructions for Menfre01/waveloom, covering waveloom, 项目概要, 编码规范, 代码审查 and 开发流程.

Menfre01/waveloom · 3,069 tokens

ssm AGENTS.md

Instructions for lfaoro/ssm, covering ssm — agent working instructions, the prime directive, 2. non-negotiable rules, 3. architecture contracts (must remain true) and ssh config parser (pkg/sshconf).

lfaoro/ssm · 1,989 tokens

go-proxmox CLAUDE.md

Instructions for luthermonson/go-proxmox: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

luthermonson/go-proxmox · 90 tokens