agentmods.dev

remote

A live phone and browser controller for Grok Build, a coding tool, with a session picker and real-time updates.

In plain words
What is it for?
Use it to start, stop, or check the remote service, load sessions, watch live work, use skills, or create a task in a selected working folder.
Why use it?
It gives you remote access to Grok Build's sessions, thoughts, tool activity, plans, and task creation from one phone page.

Skill for Claude CodeCodex

5 6d ago A scan 51 tokens original MIT
View the source file Amnibro/grok-remote
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 skills/amnibro/grok-remote/remote
Any agent
npx skills add Amnibro/grok-remote --skill remote
Clone the repo
git clone --depth 1 https://github.com/Amnibro/grok-remote

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,807 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00051 $0.01807
Opus 5 $0.00026 $0.00903
Sonnet 5 $0.00010 $0.00361
Haiku 4.5 $0.00005 $0.00181

Measured 2d ago against content hash 6fe039764727, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

remote 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.

skills/remote/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grok Remote (/remote) v1.1

Start (or manage) Grok-Remote: a live phone controller for Grok Build (not history-only).

What it does

  1. Runs grok agent --always-approve --leader serve on 127.0.0.1:2419 (tools on this PC).
  2. Runs UI + WebSocket proxy on 0.0.0.0:2421 (one phone URL; secret server-side).
  3. Phone: session picker, full history (msgs/thoughts/tools/plans), live stream + catch-up poll, Skills palette, New Task (cwd), back-swipe → Sessions.

Plugin paths

  • Plugin root: use GROK_PLUGIN_ROOT if set, else the directory that contains start.ps1 / server.py for this plugin.
  • Scripts: $PLUGIN/start.ps1, $PLUGIN/server.py, $PLUGIN/web/index.html
  • Data/logs: prefer GROK_PLUGIN_DATA when set, else $PLUGIN/logs

Arguments ($ARGUMENTS)

Parse the first token:

Arg Action
(empty) or start Start/heal single stack (ensure-running.ps1 -Force -IgnoreConfig) — kills older listeners on control ports first
stop Run scripts/stop-remote.ps1 — only listeners on 2421 + 2419 (never Stop-Process -Name grok)
status Run scripts/status-remote.ps1 — loud MODE (HEALTHY / UI_ZOMBIE / STOPPED), ports, PIDs, hub_clients
url Print the LAN connect URL only
task <cwd> [message…] Tell the user the phone Task button / deep link for a new session at cwd
extra path Optional cwd override after the verb

UI stop + pin

  • Header Stop posts /api/stack/stop (stops UI + remote agent serve; desktop TUI stays)
  • Header Pin posts /api/stack/shortcut → Desktop + Start Menu shortcuts
  • Desktop: Grok Remote / Grok Remote Stop; Start Menu folder Grok Remote
  • Pin to taskbar: right-click Desktop shortcut → Pin to taskbar

Phone UI features (tell the user)

  • Live stream of desktop + phone turns (plus 0.8s catch-up poll for missed PC-side messages)
  • Back swipe / ‹ returns to Sessions (does not leave the site)
  • Skills button → slash commands for the active session
  • Task → new session at a stated folder + optional first prompt
  • Theme → UX: auto-scroll, collapse think/code/tools, borders vs clean UI (device localStorage)
  • ↓ Latest FAB when scrolled up in chat
  • Deep links: ?auto=1&session=<id> · ?auto=1&task=<msg>&cwd=<path>

Read the full file on GitHub · 145 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 · 145 lines · 51 tokens per session scan A 6fe039764727

Subscribe to this mod's changes

remote is a skill published in the GitHub repository Amnibro/grok-remote (5 stars, last pushed 6d ago), licensed MIT. It adds 51 tokens to every session and 1,807 once invoked, about $0.0003 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.

Browser automationMobile
Related

Other skills, from other repositories

canvas

Display, present, and render HTML content on connected Otto nodes (Mac app, iOS, Android). Show on device, preview on mobile, push to screen, or navigate to a URL on any connected node. Use for games, visualizations, dashboards, interactive demos, and live-reloading development previews. Supports presenting, hiding…

elizaOS/eliza · 91 tokens

ios-simulator-browser

Stream an explicit iOS Simulator through pinned serve-sim into the T3 Code in-app browser or another agent browser. Use on Apple Silicon macOS when the user should watch simulator verification live or when browser-visible simulator evidence is needed.

pingdotgg/t3code · 52 tokens

argent-device-interact

Interact with an iOS simulator, Android emulator, or Chromium (CDP) app using argent MCP tools. Use when tapping UI elements, performing gestures, scrolling/swiping, typing text, pressing hardware buttons, launching apps, opening URLs, taking screenshots, waiting for an element to appear or disappear, or checking…

software-mansion/argent · 73 tokens

argent-tv-interact

Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…

software-mansion/argent · 107 tokens

asc-app-create-ui

Create a new App Store Connect app record via browser automation. Use when there is no public API for app creation and you need an agent to drive the New App form.

rorkai/app-store-connect-cli-skills · 39 tokens

android-ui-automation

Automate Android apps that have no public API or web version by driving the UI layer through the Accessibility Service. Handles: deep-link launch (open an app into a specific screen), intelligent node location (find a button or text by fuzzy match, not exact text), tap-and-verify (confirm an action had its effect)…

OpenMinis/MinisSkills · 171 tokens