gnome-ui-mcp: Instructions file for Codex

AGENTS.md

gnome-ui-mcp AGENTS.md is an instructions file for Codex, OpenCode from asattelmaier/gnome-ui-mcp. It costs 486 tokens per session, scanned A, original, MIT.

A set of AGENTS.md instructions for a Python MCP server and command-line tool that controls a GNOME Linux desktop. It describes the project's commands, code structure, and preferred way to inspect and operate the desktop.

In plain words
What is it for?
It is for running checks and tests, formatting and linting Python code, regenerating tool documentation, and navigating the desktop by taking a snapshot before acting.
Why use it?
It gives coding agents the project rules they need to make compatible changes and avoid crossing its architecture boundaries.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is asattelmaier/gnome-ui-mcp's own configuration. It tells Codex and OpenCode how to work on gnome-ui-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gnome-ui-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to asattelmaier/gnome-ui-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/asattelmaier/gnome-ui-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/asattelmaier/gnome-ui-mcp

Made for: Codex, OpenCode.

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 gnome-ui-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/asattelmaier/gnome-ui-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/asattelmaier/gnome-ui-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/asattelmaier/gnome-ui-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/asattelmaier/gnome-ui-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for gnome-ui-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/asattelmaier/gnome-ui-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/asattelmaier/gnome-ui-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 486 This file is loaded in full into every session.
When invoked 486 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00486 $0.00486
Opus 5 $0.00243 $0.00243
Sonnet 5 $0.00097 $0.00097
Haiku 4.5 $0.00049 $0.00049

Measured 8d ago against content hash 0b8dfa145953, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gnome-ui-mcp 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 8d 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 · 44 lines

What it actually says

Agent guide

This repository is an MCP server and CLI for automating a GNOME Wayland desktop through AT-SPI (discovery) and Mutter RemoteDesktop (input).

Commands

  • ./scripts/check.sh — full verification suite (sync, lint, format, tests).
  • uv run pytest tests -q — run all tests.
  • uv run pytest path/to/test.py -q — run a single test file.
  • uv run ruff check src tests scripts — lint.
  • uv run ruff format src tests scripts — format.
  • uv run python scripts/generate_docs.py — regenerate the tool reference after changing tool definitions.

Rules for Python

  • Do not use Any, bare except:, cast(...), or # type: ignore.
  • Tools are declarations (define_tool); handlers return None and mutate the McpResponse. Layering is strict and one-directional: tools/ -> adapters/ -> desktop/ -> runtime/gi_env.py.
  • Desktop modules return {"success": bool, ...} and never raise across the boundary; adapters flip failures into exceptions; the dispatcher in server.py formats them.

Drive the desktop snapshot-first — take a snapshot, then act on uids:

  1. take_snapshot — capture the active window (or pass window from list_windows, or app_name). Returns a compact tree where every element has a stable uid like 7_42.
  2. click / fill / hover / fill_form — reference elements by uid. Actions auto-wait for the UI to settle and report effect verification. Pass include_snapshot=true to see the result in the same turn.
  3. If a uid is rejected as stale (the UI changed), call take_snapshot again and use a fresh uid. uids are only valid for the latest snapshot.

select_window sets the implicit snapshot scope. The lower-level path-based tools (find_elements, click_element, set_element_text, ...) remain available as advanced building blocks.

See docs/design-principles.md and docs/architecture.md for the full model.

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. 8d ago First seen · 44 lines · 486 tokens per session scan A 0b8dfa145953

Subscribe to this mod's changes

gnome-ui-mcp AGENTS.md is an instructions file published in the GitHub repository asattelmaier/gnome-ui-mcp (1 stars, last pushed 24d ago), licensed MIT. It adds 486 tokens to every session, about $0.0024 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens