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.
npx skills add segentic-lab/glovebox-mcp --skill gloveboxgit clone --depth 1 https://github.com/segentic-lab/glovebox-mcpWrote 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.
[](https://agentmods.dev/skills/segentic-lab/glovebox-mcp/glovebox)<a href="https://agentmods.dev/skills/segentic-lab/glovebox-mcp/glovebox"><img src="https://agentmods.dev/badge/skills/segentic-lab/glovebox-mcp/glovebox/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.
<a href="https://agentmods.dev/skills/segentic-lab/glovebox-mcp/glovebox"><img src="https://agentmods.dev/badge/skills/segentic-lab/glovebox-mcp/glovebox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00277 | $0.02064 |
| Opus 5.5 | $0.00111 | $0.00826 |
| Sonnet 5.5 | $0.00055 | $0.00413 |
| Haiku 4.5 | $0.00028 | $0.00206 |
Grade A, and why
glovebox 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Driving apps with Glovebox
Glovebox gives you a real app in a real window that only you can see and
touch: each instance is its own X display (:2, :3, …) with its own cursor,
keyboard focus and clipboard, rendered as a window on the person's desktop. You
act with pixels and keys, like a person would, and you look before you act.
Every tool answers JSON with ok and, on failure, fix — the call that
unblocks you. Read fix and do what it says before trying anything else.
First moves
status()— version, the vision backend actually in use (vision.effective:local= OmniParser/ScreenParser on the GPU,basic= tesseract OCR,none= your own eyes), running instances, missing system deps,notes.list_instances()— what is already running (other agents' windows showlaunched_here: falseand atitle). Never drive another agent's instance; launch your own.launch_app("chromium")/launch_app("gimp", size="1600x1000")→ use the returnedinstanceid in EVERY call. Checkwarnings.wait_for_stable(instance)thenscreenshot(instance)— the app needs a moment to draw.
The loop
Look → act → verify. You cannot see the screen unless you take a
screenshot or parse_screen; after every action that changes the screen,
observe again. The cheap way: pass observe="screenshot" (or "parse") and a
settle_ms on the action itself, or wait_for_stable / wait_for_text after
navigation. Then confirm the result before the next step. Ids from
parse_screen/find_elements go stale the moment the screen changes.
Grounding: how to know where to click
| Vision mode | How to find a target |
|---|---|
local (GPU) |
find_elements("Save", instance, type="button") → click_element(id). Elements have real types (button/link/tab/input/checkbox/…) with the ScreenParser detector; parse_screen lists everything (capped at 300, truncated flagged). |
basic (OCR) |
find_elements("Sign in", instance) finds text lines; icons without text are invisible to OCR — screenshot + click(x, y) for those. |
none |
screenshot(instance), reason about pixel coordinates yourself, click(x, y). Zoom with region="x,y,w,h" for small text. |
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.
- yesterday Changed · +11 lines 7ac241b9a85f
- 2d ago First seen · 108 lines · 277 tokens per session scan A ca88c4193b6a
glovebox is a skill published in the GitHub repository segentic-lab/glovebox-mcp (13 stars, last pushed yesterday), licensed MIT. It adds 277 tokens to every session and 2,064 once invoked, about $0.0011 per session on Opus 5.5. 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 2026-11-14.
glovebox compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gloveboxsegentic-lab/glovebox-mcp | Skill | 13 | yesterday | MIT | A | 277 | Claude Code, Codex |
| trusty-squireTrusty-Squire/trusty-squire | Skill | 3 | yesterday | MIT | A | 208 | Cursor |
| browserstickerdaniel/browserjack | Skill | 5 | 6d ago | MIT | A | 18 | Claude Code |
| signed-in-browsert3ratech/mcp-session-bridge | Skill | 2 | 3d ago | Apache-2.0 | A | 109 | Claude Code, Codex |
| post-to-hacker-newst3ratech/mcp-session-bridge | Skill | 2 | 3d ago | Apache-2.0 | A | 75 | Claude Code, Codex |
| melaya-setupmelaya-labs/melaya-mcp | Skill | 1 | 2d ago | Apache-2.0 | A | 119 | Claude Code |
| ciso-phishing-mailbox-safetymelaya-labs/melaya-mcp | Skill | 1 | 2d ago | Apache-2.0 | A | 88 | Claude Code |