Tokenmonitor — AI skill for Claude Code
See what your AI coding tools actually use and cost — token usage & estimated spend for Claude Code, Codex CLI, and Gemini CLI.
How to install Tokenmonitor
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open louisnwadike52-design/tokenmonitor and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Tokenmonitor does
See what your AI coding tools actually use and cost — token usage & estimated spend for Claude Code, Codex CLI, and Gemini CLI. 100% local, zero dependencies.
Alternatives in AI
- Codeburn — Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Code 9.7k ★
- TokenTracker — Local-first AI token usage & cost tracker for 31 coding tools incl 1.4k ★
- Snip — CLI proxy that reduces LLM token usage by 60-90% 425 ★
README
tokenmonitor
[](https://github.com/louisnwadike52-design/tokenmonitor/actions/workflows/ci.yml) [](LICENSE) [](package.json) [](package.json)
**See what your AI coding tools actually use and cost — one command, 100% local.**
`tokenmonitor` reads the session logs your AI CLIs already write to disk and reports token usage and estimated spend across all of them:
| Tool | Logs read | Notes |
|---|---|---|
| Claude Code | ~/.claude/projects/**/*.jsonl ($CLAUDE_CONFIG_DIR overrides) |
dedupes resumed sessions; 5m/1h cache-write TTLs priced separately |
| OpenAI Codex CLI | $CODEX_HOME/sessions (default ~/.codex/sessions) |
per-request deltas; cached input priced at the discounted rate |
| Gemini CLI | $GEMINI_DIR (default ~/.gemini) |
best-effort scan of session metrics and chat transcripts |
No API keys, no accounts, no telemetry, no network calls — it never leaves your machine.
Install
npm install -g tokenmonitor # or: npx tokenmonitor
From source (zero dependencies — there is nothing to `npm install`):
git clone https://github.com/louisnwadike52-design/tokenmonitor.git
cd tokenmonitor && npm link
Usage
tokenmonitor # usage by tool + model (default)
tokenmonitor daily # usage by day
tokenmonitor models # usage by model
tokenmonitor plans # list known subscription plans
$ tokenmonitor daily --since 2026-09-05
Date Input Output Cache Read Cache Write Total Est. Cost
──────────────────────────────────────────────────────────────────────────────────
2026-09-05 4,933 1,642,150 1,338,074,425 11,017,526 1,350,739,034 $816.0
Related Skills
Retok
Token-efficiency analyzer for AI coding agents (Claude Code, OpenAI Codex CLI): cost estimates, cache analysis
AI Harness Character Creator
AgentDeck: one local GUI to configure every AI coding agent. Tune behavior, permissions, token usage and cost,
Spoor
Local-first LLM observability. Inspect agent traces, token usage, latency and estimated costs with one binary
Xiaoyaoclaw Usage Report
OpenClaw usage & performance reporting - parse session JSONL for task duration, tool/skill/model usage, token
Token Ledger
Know what your AI coding agents actually cost. A tiny macOS menu bar app for Claude Code, Codex, Droid, Pi, De
ToastMonitor
Native macOS menu-bar AI usage monitor. Aggregates token usage from Claude Code, Codex, OpenCode, Hermes, Oh M
Related Agents
Stats Analyzer
Analyzes ~/.claude/stats-cache.json and history.jsonl to produce a concise usage report with model token break
Usage Reporter
Reads real Claude Code usage from ~/.claude/stats-cache.json. Reports daily/weekly token usage by model, cache
Budget
AI cost engineering — LLM spend tracking, model cost optimization, budget alerts, token efficiency audits