Herdr Agent Usage — AI skill for Claude Code
Credential-scoped AI quota, context, and cache in Herdr for Claude, Codex, Grok, Agy, OpenCode, Pi, omp, Devin, Muse, and Cursor.
How to install Herdr Agent Usage
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open levi-qiao/herdr-agent-usage and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Herdr Agent Usage does
Credential-scoped AI quota, context, and cache in Herdr for Claude, Codex, Grok, Agy, OpenCode, Pi, omp, Devin, Muse, and Cursor.
Alternatives in AI
- EchoBird — One-click install + model switch:Claude Code,Codex CLI (OpenAI), Grok Build (xAI), DeepSeek Harness, Kimi Code 3.1k ★
- Token Monitor — Local-first desktop widget for tracking token usage, costs, and limits across 32+ AI coding tools—including Cl 1.8k ★
- Claudexor — Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple 425 ★
README
herdr-agent-quota
Model, context, and subscription quota in Herdr's Agent sidebar — grouped by Space, with brand icons that carry agent status.
[](https://github.com/levi-qiao/herdr-agent-quota/actions/workflows/ci.yml) [](LICENSE)
[简体中文](README.zh-CN.md)
Agents are grouped under their Space. Each row leads with this plugin's brand icon — not Herdr's status ring. The icon colour tracks the agent: yellow while working, teal while done (until you focus it or move focus away from it), ink-white when idle. Provider and model stay ink-white; severity colours on the meters still mean remaining headroom.
The default layout is `gauges`: a meter beside each quota number. Bars fill to the printed number, and `cx`, `5h`, `7d`, and `30d` all follow `quota-percent`. Labels are three characters so those periods align; a provider-named window too long for that column keeps a plain row instead of a truncated bar. Meters size to the connected Herdr endpoint's sidebar — indent and scrollbar included. Empty fields collapse; percentages can show remaining or used quota. Cache and TTL are off by default (turn them on in settings if you want them). Login-scoped vendors (Grok, Codex, Devin, OpenCode, Cursor) keep every tab visible in the Agent panel; duplicate 5h/7d/30d rows collapse to one pane per Space. On a wide sidebar, the vendor icon and name sit above that pane's quota, and extra tabs list model, topic, and context with no icon. A settings row gap of 1 still separates different agents; nested extra tabs of the same vendor stay flush. Claude and Agy stay per-pane. Agent order defaults to Space grouping with least quota left first inside each space. Low-quota notifications stay off until you set a threshold. Switch layout, fields,
Related Skills
AgentBridge
Migrate AI coding agent config between 12 agents — Claude Code, Codex, Copilot, Cursor, Gemini, Crush, Grok, o
Select Coder
Recommend which coder agent and model should execute a coding task — probes locally available backends (opus,
AI Quota Deck
A Windows tray dashboard for Claude Code, Codex, Gemini, and Grok usage limits.
AI Usage Dashboard
Local-first quota cockpit for Claude Code, Codex, Grok Build, and DeepSeek API balance on Windows, macOS, and
Token Watcher
⏱ Token Watcher — local real-time token usage & quota dashboard for AI coding agents (Claude Code, ccmr, Codex
KodexBar Suite
Linux AI quota monitor and KDE Plasma 6 widget for Claude Code, OpenAI Codex, Cursor, Grok, OpenCode Go, and A
Related Agents
10x Tool Calls
Cursor and Windsurf meter usage by requests and tool calls rather than tokens, which means a finished or stall
Benchmark Agent
Use this agent for competitive intelligence and platform benchmarking — it obsessively tracks where Cursor, De
Cursor Delegate
Proactively use when this coding agent should hand a substantial coding, diagnosis, or implementation task to