glovebox-mcp: Instructions file for Codex

AGENTS.md

glovebox-mcp AGENTS.md is an instructions file for Codex, OpenCode from segentic-lab/glovebox-mcp. It costs 1,523 tokens per session, scanned A, original, MIT.

Operating instructions for using Glovebox, a tool that lets an agent control an isolated desktop window through screenshots and actions.

In plain words
What is it for?
Use it when opening, inspecting, clicking, typing in, or troubleshooting applications inside a Glovebox desktop instance.
Why use it?
It explains how to interpret success and error responses and how to recover from problems such as a dead window or an invalid element reference.

Instructions file for CodexOpenCode

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

This is segentic-lab/glovebox-mcp's own configuration. It tells Codex and OpenCode how to work on glovebox-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 glovebox-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to segentic-lab/glovebox-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/segentic-lab/glovebox-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/segentic-lab/glovebox-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 glovebox-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/segentic-lab/glovebox-mcp/agents-md.svg)](https://agentmods.dev/instructions/segentic-lab/glovebox-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/segentic-lab/glovebox-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/segentic-lab/glovebox-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,523 This file is loaded in full into every session.
When invoked 1,523 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 $0.01523 $0.01523
Opus 5 $0.00762 $0.00762
Sonnet 5 $0.00305 $0.00305
Haiku 4.5 $0.00152 $0.00152

Measured 7d ago against content hash 303f25df0fd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

glovebox-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 7d 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 · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

glovebox-mcp — instructions for the agent

Paste this into the system prompt / context of any AI agent that will use the glovebox MCP tools. It teaches the agent how to drive the sandbox well and avoid the traps.


You are driving a real, sandboxed desktop through the glovebox MCP tools. Everything you do happens inside a nested X11 window (an "instance"), isolated from the user's real screen and files.

Responses: read ok and fix

Every tool returns JSON: {"ok": true, "action": …, "instance": …, …}. When a call fails, the result is flagged as an error and contains {"ok": false, "error": …, "fix": …}fix names the exact call that unblocks you (re-run parse_screen, check list_instances, etc.). Follow it instead of retrying blindly. The server never reports success for something that didn't happen: a dead instance, an unknown element id, an invalid key name, a zero scroll all come back as errors. Start with status() to see the vision backend, live instances, and installed deps in one call.

Mental model

  • Each instance (instance=N, default 1) is one app window on its own display. You cannot see it unless you take a screenshot or parse_screen. Always look before you act.
  • Work observe → act → verify. Never fire a sequence of clicks without confirming the screen changed the way you expected.
  • Coordinates are absolute pixels within that instance's display (top-left origin).

The core loop

  1. Lookscreenshot(instance) to see the screen, or parse_screen(instance) to get detected elements with ids + pixel-centers.
  2. Actclick, type_text, press_keys, scroll, drag, click_element, upload_file.
  3. Verify — pass observe="screenshot" (or "parse") to the action and it returns the resulting screen in the same call (no extra round-trip). Add settle_ms=400..1500 after anything that triggers loading/navigation so the UI settles before the screenshot.

Grounding: how to know WHERE to click

Read the full file on GitHub · 111 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. 7d ago First seen · 111 lines · 1,523 tokens per session scan A 303f25df0fd1

Subscribe to this mod's changes

glovebox-mcp AGENTS.md is an instructions file published in the GitHub repository segentic-lab/glovebox-mcp (13 stars, last pushed 2mo ago), licensed MIT. It adds 1,523 tokens to every session, about $0.0076 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

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 · 5,182 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

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

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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens