agentmods.dev

deskbrid AGENTS.md

Project instructions for Deskbrid, a daemon that lets an AI agent control a Linux desktop through a local Unix socket. It can work with windows, keyboard and mouse input, clipboards, screenshots, and system information.

In plain words
What is it for?
Use it to list or arrange windows, type and click, read or write the clipboard, capture or compare screenshots, and inspect desktop or system status.
Why use it?
It explains how to install, start, communicate with, and test the desktop-control service in the repository.

Instructions file for CodexOpenCode

30 28d ago A scan 1,036 tokens original MIT
View the source file coe0718/deskbrid
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/coe0718/deskbrid/agents-md
Clone the repo
git clone --depth 1 https://github.com/coe0718/deskbrid

Made for: Codex, OpenCode.

Per session 1,036 This file is loaded in full into every session.
When invoked 1,036 The same file — it is already loaded in full.
Security scan A 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 $0.01036 $0.01036
Opus 5 $0.00518 $0.00518
Sonnet 5 $0.00207 $0.00207
Haiku 4.5 $0.00104 $0.00104

Measured 2d ago against content hash a5e93bd74a02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deskbrid AGENTS.md scanned grade A 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

bash <(curl -fsSL https://deskbrid.patchhive.dev/install.sh)
AGENTS.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deskbrid

Deskbrid bridges AI agents to any Linux desktop over a Unix socket. Control windows, inject keystrokes, take screenshots, manage clipboards — on GNOME, KDE, Hyprland, COSMIC, Sway, Niri, Wayfire, Labwc, or X11.

Install

bash <(curl -fsSL https://deskbrid.patchhive.dev/install.sh)

Auto-detects distro + DE, installs deps, sets up uinput, downloads binary.

Quick Start

deskbrid daemon                               # start daemon
deskbrid windows list                         # CLI: list windows
deskbrid clipboard read                       # CLI: read clipboard
deskbrid screenshot                           # CLI: screenshot

# Socket (agent-native)
echo '{"type":"system.info","id":"1"}' | nc -U $XDG_RUNTIME_DIR/deskbrid.sock -w 2
echo '{"type":"windows.list","id":"2"}' | nc -U $XDG_RUNTIME_DIR/deskbrid.sock -w 2

Features

  • Windows & Workspaces — list, focus, close, minimize, maximize, tile, move/resize
  • Input — keyboard typing, key combos, mouse control
  • Clipboard — read/write with history
  • Screenshots — capture, OCR, diffing
  • System — info, battery, idle, power management, pressure (PSI)
  • Audio — volume, mute, sink management
  • Network & Bluetooth — WiFi, device pairing
  • Vision — element detection, text recognition, state detection via Tesseract OCR (vision.find_element, vision.find_by_text, vision.detect_state)
  • Storage — disk usage stats and filesystem scanning (storage.usage, storage.scan)
  • Monitor DDC/CI — brightness, contrast, input source, power over I2C without compositor
  • MPRIS — media player control
  • Terminal — PTY sessions
  • Files — search, read, write, watch
  • Notifications — send, dismiss, history
  • Speech — text-to-speech via spd-say/espeak-ng (speech.speak, speech.stop, speech.voices)
  • Keyboard Layouts — list, switch, add, remove
  • Desktop Settings — gsettings read/write, schema discovery (GNOME, KDE, X11, Hyprland, Sway, COSMIC, Labwc, Niri, Wayfire)
  • Backlight — list, get, set brightness via sysfs (all backends)
  • Print — list printers, set default, list/cancel/pause/resume jobs, send files to printer (CUPS)
  • Self-update — deskbrid update pulls latest from GitHub releases
  • Confirmation Mode — require explicit approval for destructive actions before execution
  • Agent Messaging — inter-agent mailbox for message passing between sessions
  • Unified Search — cross-surface search (windows, apps, files, clipboard, audit log) with relevance scoring
  • Keyring Access — Secret Service integration for secure credential storage and retrieval
  • Rate Limiting — per-namespace, per-agent token bucket limits (configurable via permissions.toml)
  • Sandboxed Profiles — named agent profiles with allow/deny/confirm gates, profile-scoped rate limits
  • Auto-Suspend — dangerous command blocking, burst detection, heartbeat timeout canary suspension
  • Locks — distributed resource locks for multi-agent coordination with token-based ownership
  • Region Watching — screen region monitoring with text-change detection
  • Agent Registry — session and agent tracking for multi-agent coordination

Read the full file on GitHub · 91 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 · 91 lines · 1,036 tokens per session scan A a5e93bd74a02

Subscribe to this mod's changes

deskbrid AGENTS.md is an instructions file published in the GitHub repository coe0718/deskbrid (30 stars, last pushed 28d ago), licensed MIT. It adds 1,036 tokens to every session, about $0.0052 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Browser automation
Related

Other instructions, from other repositories

Browser4 CLAUDE.md

Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.

platonai/Browser4 · 1,205 tokens

agentic-playwright selectors.instructions.md

Instructions for idavidov13/agentic-playwright, covering selector strategy, critical, instructions, phase 1: open and authenticate and phase 2: explore like a user.

idavidov13/agentic-playwright · 2,174 tokens

scrapai-cli CLAUDE.md

Instructions for discourselab/scrapai-cli, covering claude.md, 1. who you are, 2. hard rules, 3. tools and 4. before you start: confirm the project.

discourselab/scrapai-cli · 8,964 tokens

chromeboost CLAUDE.md

Instructions for lordamdal/chromeboost, covering chromeboost — repo-developer guide, what chromeboost is, repository layout, development commands and tests/antibot/ (run locally; not in ci).

lordamdal/chromeboost · 3,633 tokens

skills CLAUDE.md

Instructions for aemcoder/skills, covering claude.md, repository structure, slicc browser automation conventions, stateless tab targeting (since slicc pr #188) and tab-new returns a targetid.

aemcoder/skills · 1,546 tokens

xgrower-extension CLAUDE.md

Instructions for JoyyyceD/xgrower-extension, covering x grower extension — architecture notes, architecture, key files, auth flow and quota system.

JoyyyceD/xgrower-extension · 900 tokens