OpenGUI AGENTS.md

Repository instructions for developing and checking the OpenGUI project, including its desktop and web commands, translations, and project rules.

In plain words
What is it for?
Use them when developing OpenGUI, running its desktop or web version, checking code, running tests, or creating a production build.
Why use it?
They give contributors the project-specific commands and constraints needed to run, check, test, and build it consistently.

Instructions file for CodexOpenCode

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/akemmanuel/opengui/agents-md
Clone the repo
git clone --depth 1 https://github.com/akemmanuel/OpenGUI

Made for: Codex, OpenCode.

Per session 661 This file is loaded in full into every session.
When invoked 661 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 $0.00661 $0.00661
Opus 5 $0.00331 $0.00331
Sonnet 5 $0.00132 $0.00132
Haiku 4.5 $0.00066 $0.00066

Measured 2d ago against content hash 5c1d882aeeea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

OpenGUI AGENTS.md 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.

AGENTS.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Default to using Vite+ (vp) instead of raw runtime or package-manager commands. Vite+ is a dev dependency: use pnpm vp <command> when vp is not on PATH, or pnpm run <script> when package.json defines the task.

  • Use pnpm run dev for desktop development (Electron); use pnpm run dev:web for web (append :web to the dev task)
  • Use pnpm run start for desktop production; use pnpm run start:web for web (append :web to the start task)
  • Use vp check (or pnpm run check) for lint, format, and type checks
  • Use vp lint (or pnpm run lint) for lint only
  • Use vp fmt (or pnpm run fmt) for format only
  • Use vp test (or pnpm run test) for tests
  • Use run build for production build
  • Use vp run <task> or pnpm run <script> for project tasks
  • Use vp exec <command> for local binaries
  • Use node --experimental-strip-types <file> for project TypeScript scripts (or pnpm vp node when Vite+ env shims are installed)
  • Use vp dlx <package> <command> for one-off package binaries
  • Use vp cache for task cache
  • Use pnpm install to install dependencies
  • Use pnpm add, pnpm remove, pnpm update, etc. for dependency changes
  • Use pnpm run <script> for package scripts
  • Do not use npm or yarn in project instructions unless code specifically requires them.

Development

Run the app with pnpm run dev or pnpm run start on desktop; for the browser stack, use the same task with :web (pnpm run dev:web, pnpm run start:web). Use Vite+ (vp) for lint, format, typecheck, test, and build—not for choosing dev vs prod.

Code quality

  • Run pnpm run slop-check when changing Host routes, Session paths, or frontend Host transport
  • Prefer vp check before submit
  • Prefer vp lint / vp fmt when narrowing issues
  • Use pnpm run only when task is defined in package.json

Translations

When adding or changing user-facing text, update i18n files in src/i18n/locales/ at same time.

  • Add or update keys in en.json, de.json, and es.json
  • Do not leave hardcoded UI strings in React components when text should be translated
  • Keep locale key structure aligned across all supported languages

Read the full file on GitHub · 48 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. 2d ago First seen · 48 lines · 661 tokens per session scan A 5c1d882aeeea

Subscribe to this mod's changes

OpenGUI AGENTS.md is an instructions file published in the GitHub repository akemmanuel/OpenGUI (107 stars, last pushed 20d ago), licensed MIT. It adds 661 tokens to every session, about $0.0033 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 2026-08-30.

Related

Other instructions, from other repositories