Herdr Agent Quota — Productivity skill for Claude Code
Live Claude, Codex, Grok & Agy quota monitoring for Herdr — usage, reset times, task context, and time-aware quota health dynamically calculated from your remaining quota and runway.
How to install Herdr Agent Quota
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open levi-qiao/herdr-agent-quota and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Herdr Agent Quota does
Live Claude, Codex, Grok & Agy quota monitoring for Herdr — usage, reset times, task context, and time-aware quota health dynamically calculated from your remaining quota and runway.
Alternatives in Productivity
- Skill Cost Projections — Project remaining workflow cost from per-phase averages — warns on budget ceiling overruns 2.8k ★
- GrokSearch — Integrate Grok's powerful real-time search capabilities into Claude via the MCP protocol 1.8k ★
- Claude Code Hooks Multi Agent Observability — Real-time monitoring for multi-agent Claude Code sessions via hook event tracking 1.3k ★
README
herdr-agent-quota
**Never hit a quota limit mid-task.** Live Claude Code, Codex, Grok, and Agy/Antigravity subscription usage, in Herdr's agent sidebar.
[](https://github.com/levi-qiao/herdr-agent-quota/actions/workflows/ci.yml) [](https://www.rust-lang.org/) [](https://herdr.dev/docs/plugins/) [](LICENSE) [](https://github.com/levi-qiao/herdr-agent-quota)
中文文档:[README.zh-CN.md](README.zh-CN.md)
● Owner · Claude/Sonnet
hi ← what that pane is actually working on
cache 99.6% · ttl≈58m ← session hit rate · remaining cache TTL
context 23% ← provider-native context percentage
5h 100% 3h07m · 7d 31% 2d3h

*A current Herdr workspace: Claude and Codex show five-hour and weekly reset ETAs on one compact row, Grok keeps its `7d` window clean when Herdr has no session id, and Agy shows model/context/cache data from its matching statusLine session. Each card uses the latest user prompt rather than an AI-generated status.*
- Four providers, one sidebar — Claude Code, OpenAI Codex, Grok, and Agy/Antigravity.
- Compact, capability-aware cards — provider, prompt/session summary, supported context usage, and quota windows. Unsupported rows are hidden.
- Local only — no usage data uploaded, no browser cookies, no keychain scraping, and credentials are never written or refreshed.
- Never lies to you — a failed refresh keeps the last good number instead
of flashing
unavailable, and API-key auth is never shown as a subscription
Related Skills
Claude CLI Session Monitor
Real-time monitoring dashboard for Claude Code CLI sessions — track token usage, session health, and context w
Cha Review2
Send every pending briefing to the second eye — one at a time, quota-aware, skipping anything already answered
Crackerjack Status
Check comprehensive Crackerjack system status including running jobs, MCP server health, WebSocket connections
Workflow Maintenance
Recurring workflow maintenance — capture live self-improvements, curate learnings, check trunk health. Idempot
Claude Code Usage Bar
Real‑time statusline for Claude Code: token usage, remaining budget, burn rate, and depletion time.
Usage Buddies
Real-time Claude usage limits, session pace, weekly quotas and service health in your KDE panel, tray or Windo
Related Agents
Usage Scout
Read-only scout for session, token, and cost code in this FastAPI tracker. Use when the user asks where usage
10x Tool Calls
Cursor and Windsurf meter usage by requests and tool calls rather than tokens, which means a finished or stall
MLOps Orchestrator
Orchestrates LibreMLOps Grok skills — experiments, eval, RAG, deploy, monitoring. Melt carefully vs Reality OS