Firetv Agent Monitor — AI skill for Claude Code
Your AI coding agents on a Fire TV: Claude Code, Codex, Muse Code and GoodVibes sessions with live status, activity, context, plan usage and a read-only session view.
How to install Firetv Agent Monitor
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open mgd34msu/firetv-agent-monitor and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Firetv Agent Monitor does
Your AI coding agents on a Fire TV: Claude Code, Codex, Muse Code and GoodVibes sessions with live status, activity, context, plan usage and a read-only session view. Built from lg-agent-monitor and rokuagents.
Alternatives in AI
- Ccstatusline — by sirmalloc - A highly customizable status line formatter for Claude Code CLI that displays model info, git b 5.5k ★
- Token Monitor — Local-first desktop widget for tracking token usage, costs, and limits across 32+ AI coding tools—including Cl 1.8k ★
- Syrtis — AI token usage & quota monitor for the macOS menu bar — native Swift, Liquid Glass, 3D contribution graph 368 ★
README
Fire TV Agent Monitor
Every AI coding agent you have open, on your Fire TV: which one is working, which one needs you, and how much of your plan is left.
Each open session is a card: green while it works, yellow when it waits for you, red when it failed, dimmed once it has been idle for hours. A card names the tool, the session's title and folder, what the agent is doing right now (or what it asked you), how long it has been in that state, and a bar for context-window usage. The right third of the screen shows how much of each subscription's 5-hour and weekly limits is used, and the context of every session. Select a card to read that session's conversation, read only.
This is the Fire TV version of [lg-agent-monitor](https://github.com/mgd34msu/lg-agent-monitor), which forks [rokuagents](https://github.com/jonsykes/rokuagents) by Jon Sykes, itself a fork of [managents](https://github.com/tonylook/managents) by Antonio Alvino. See [Credits](#credits).
Supported agents
| Agent | Status | What it is doing | Context | Plan limits |
|---|---|---|---|---|
| Claude Code | yes | yes | yes | 5-hour and weekly |
| Codex | yes | yes | yes | 5-hour and weekly |
| Muse Code | yes | yes | yes | 5-hour and weekly |
| GoodVibes | yes | yes | yes | none (no subscription) |
| OpenCode | yes | no | no | none |
Where each number comes from, all read on your computer:
| Agent | Sessions and status | Plan limits |
|---|---|---|
| Claude Code | ~/.claude/sessions and transcripts |
api.anthropic.com/api/oauth/usage with Claude Code's own login, |
Related Skills
Falaq Cockpit OSS
Mission control for Claude Code & Codex — a local dashboard to monitor, multitask, and drive all your AI codin
Lunavect
Claude Code & Codex status bar for macOS. Track AI coding sessions, usage limits and activity with native menu
AgentDeck
Mission control for AI coding agents on your Stream Deck Mini. Monitor six sessions with live status indicator
AgentStreamDeck
Mission control for AI coding agents on your Stream Deck Mini. Monitor six sessions with live status indicator
Usage Band
A live status band above the Claude Code prompt: model, context, plan limits, real prompt-cache status and cos
Claude Monitor Browser Extension
Claude Monitor: see your Claude usage limits (session, weekly, per-model, credits) live in Chrome and Firefox,
Related Agents
Abtop
AI agent monitor for your terminal. Like btop++, but for AI coding agents. Supports Claude Code and Codex CLI.
Part 13: Memory Bridge (Give Coding Agents Your Brain)
When you spawn Codex or Claude Code to build something, they start blind. They don't know your architecture de
Stats Analyzer
Analyzes ~/.claude/stats-cache.json and history.jsonl to produce a concise usage report with model token break
