Herdr Agents Tracker — AI skill for Claude Code
Herdr plugin that shows your AI subscription usage: account limits in the tab bar, a context meter per agent, low-limit alerts and a token dashboard for Claude Code, Codex, OpenCode Go and Grok.
How to install Herdr Agents Tracker
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open VHemanth45/herdr_agents_tracker and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Herdr Agents Tracker does
Herdr plugin that shows your AI subscription usage: account limits in the tab bar, a context meter per agent, low-limit alerts and a token dashboard for Claude Code, Codex, OpenCode Go and Grok.
Alternatives in AI
- Guizang Ppt Skill — AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts 24.9k ★
- Claude Usage Tracker — Native macOS menu bar app for tracking Claude AI usage limits in real-time 2.2k ★
- Context Dump — Dump current context for model switch or context limit recovery 508 ★
README
Usage Tracker for Herdr
**Every account, every limit window, every agent — and not one credential read.**
[](https://github.com/VHemanth45/herdr_agents_tracker/actions/workflows/tests.yml) [](https://herdr.dev) [](https://www.python.org/downloads/) [](LICENSE)
See how much of your AI subscriptions you have used, without leaving Herdr: in the tab bar, under each agent, and in a dashboard. Supports Claude Code, Codex, OpenCode Go and Grok.

*Screenshots use demo accounts and made-up numbers.*
What it shows
**Tab bar** — one entry per account: logo, bar, % used and time until reset, one group per limit window. A model's own limit shows its name instead of a time (`0% Fable`).

**A context meter per agent** — how full each Claude Code and Codex pane's context window is, in Herdr's Agents panel: grey, yellow from 70%, red from 90%.
**Pace** — `(100% in 4h05m)` when a limit is on course to run out before it resets.
**Alerts** — a Herdr notification when a limit passes 80% and 95%, once per window.
**Dashboard** — every window, token history, a heatmap, and totals by account, model and project.
**Several accounts per provider** — never merged; each keeps its own cache and history.
**Honest states**, never a misleading 0%: `…` first refresh · `n/a` no data source · `sign-in needed` · `error` · `(3h00m old)` stale · `~21%` estimate · `-- (reset)`.
Token
Related Skills
Gentle Agent State
See which AI coding agent needs you — right in your tmux tab bar. A colored dot per window (working/blocked/id
Burn O Meter
See what your AI coding agents really cost — tokens, spend, cache efficiency and rate limits. Works with Claud
Omarchy Agent Meter
Omarchy bar widget: AI coding usage limits (Claude Code, Codex, Fireworks) as a progress meter with the percen
Cc Token Status
new macOS menu bar dashboard for Claude Code. Shows plan usage limits, costs, tokens, trends, model breakdown,
Devie AI Quota Tracker
Dashboard + macOS menu bar for tracking AI subscription quotas in one place (Claude Code, Codex, Gemini CLI, G
Coding Agent Account Manager
Sub-100ms auth switching for AI coding CLIs (Claude Code, Codex, Gemini): swap subscription accounts instantly
Related Agents
Risk Manager
Owns the desk's risk limits, sizes every trade from live account state, monitors the book, and can veto. Read-
Cloud Manager
Owns cloud architecture across AWS/Azure/GCP — account/subscription/project structure, landing zones, networki
Playwright Skill Executor
Execute complex Playwright scripts for scenarios requiring network interception, custom retry logic, multi-tab