Agentic Metric — AI skill for Claude Code
Local-only usage monitor for Claude Code and Codex CLI sessions.
How to install Agentic Metric
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open xihuai18/agentic-metric and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agentic Metric does
Local-only usage monitor for Claude Code and Codex CLI sessions. Live TUI dashboard, per-agent and per-model cost reports, and heatmaps — nothing leaves your machine.
Alternatives in AI
- Power BI Agentic Development — Power BI AI skills and Power BI agents for Claude Code and GitHub Copilot: a plugin marketplace of Power BI sk 879 ★
- Usage — macOS menu bar & Windows tray app pinning Claude Code, Codex & Antigravity quota, burn rate, and cost to your 301 ★
- Pbi CLI — Power BI CLI - semantic models (.NET TOM) and PBIR reports for token-efficient AI agent usage, built for Claud 217 ★
README
Agentic Metric X
[](https://pypi.org/project/agentic-metric-x/) [](https://pypi.org/project/agentic-metric-x/) [](https://pepy.tech/project/agentic-metric-x) [](https://pypi.org/project/agentic-metric-x/)
[中文文档](README-CN.md)
A local and SSH remote monitoring tool for AI coding agents — like `top`, but for your coding agents. Track token usage and costs across **Claude Code** and **Codex** — with a TUI dashboard and CLI.
**Supported platforms: Linux, macOS, and Windows.**
**All data stays under your control. No telemetry is sent anywhere.** By default the tool only reads local agent data files (`~/.claude/`, `~/.codex/`). If SSH remotes are configured, it reads those remote agent data files over SSH and caches a local copy for aggregation.

Features
- Cost estimation — Per-model pricing table with CLI management, calculates API-equivalent costs; supports long-context and cache-duration pricing
- Unified report — One
reportcommand for today / week / month / custom date range, with agent × provider × model breakdown, top projects, and hourly/daily heatmaps - TUI dashboard — Terminal UI with auto-refresh, stacked summary cells, heatmap strip, adaptive 14-day / 12-week / 12-month cost trends, and agent → provider → model breakdown
- Multi-agent — Plugin architecture; supports Claude Code and Codex today, extensible
Agent Data Coverage
| Field | Claude Code | Codex |
|---|---|---|
| Session ID | ✓ | ✓ |
| Project path | ✓ | ✓ |
| Git branch | ✓ | ✓ |
| Model | ✓ | ✓ |
| Input tokens | ✓ | ✓ |
| Output tokens | ✓ | ✓ |
| Cache tokens | ✓ | ✓¹ |
| User turns | ✓ | ✓ |
| Message count | ✓ | ✓ |
| First/last prompt | ✓ | ✓ |
Related Skills
Sidekick Agent Hub
See what your AI coding agent is doing. Multi-provider assistant & session monitor for VS Code and the termina
Agent Lookout
A local dashboard for the AI agent sessions already running on your machine. Starts nothing, sends nothing.
Agenthud
Claude Code TUI dashboard: live monitor for parallel sessions and sub-agents, with LLM-generated daily/weekly
Axon
Local-first RAG engine with cited answers from your own docs. GraphRAG, sealed sharing, MCP-native, VS Code Co
Falaq Cockpit OSS
Mission control for Claude Code & Codex — a local dashboard to monitor, multitask, and drive all your AI codin
Telegram Monitor
Real-time Telegram channel monitoring with AI-powered intelligence briefings. Multi-pane TUI dashboard with Cl
Related Agents
Ade
Agent sessions routinely outlast the machine that started them, and checking a Claude Code or Codex run from a
Review UI
gleanery の端末の画面(gleanery dashboard、server/src/tui/)と CLI の出力の変更を、機械で判定できない面から確かめる独立レビュアー。server/src/tui/ か ser
Signal Monitor
Monitor PMF health, retention curves, metric volatility, and churn precursors. Use when needing PMF scores by