数据分析

TinkerClaw Token Panel

试用

Know exactly where your AI tokens go. Multi-provider tracking, budget alerts, and a local REST API—all in one dashboard. It reads Claude Code's own credential file to query Anthropic usage, calls provider usage APIs, and (opt-in) parses local session transcripts. Serves a REST API on localhost. See Permissions, Data Flow & Consent.

它能做什么

Know exactly where your AI tokens go. Multi-provider tracking, budget alerts, and a local REST API—all in one dashboard. It reads Claude Code's own credential file to query Anthropic usage, calls provider usage APIs, and (opt-in) parses local session transcripts. Serves a REST API on localhost. See Permissions, Data Flow & Consent.

技能文档

Token Panel Ultimate

One dashboard for every token you spend. Anthropic, Gemini, OpenAI, Manus—tracked, stored, and queryable before the bill arrives.

What it does that a "dashboard" does not imply:

  • It reads Claude Code's credential file (~/.claude/.credentials.json) to get an OAuth token and query Anthropic's usage endpoint. That token was issued to Claude Code, not to this tool. ClawHub's scanner flags this as credential re-use and it is right to — we are not going to soften that. If you are not comfortable with it, skip the Claude collector; every other provider works from a key you supply yourself.
  • It can parse your session transcripts, which contain your prompts and replies in full. This is opt-in and off by default: nothing is read unless you set TOKEN_PANEL_READ_TRANSCRIPTS=1. Only token counts are extracted; message text is never written to the database or returned by the API.
  • It serves a REST API. Bind it to localhost and do not expose it — it reports your usage and quota.

What it does NOT do: no silent secrets scraping (a secrets file is read only if you name it in OPENAI_ENV_FILE, and it must be an absolute, owner-only 0600 file), no message content in the database, no telemetry, no third-party endpoint.

Diagnostics are off by default. The browser widget logs nothing unless you set localStorage.BP_DEBUG = "1" — console output is readable by anything sharing the page.

Dependencies are pinned above known-vulnerable releases. The floor for fastapi is 0.109.1; the previous >=0.100.0 permitted a release affected by CVE-2024-24762.

Why This Exists

You've checked your Anthropic console, squinted at the OpenAI dashboard, opened a Gemini tab, and still weren't sure where last Tuesday's $14 went. Token Panel Ultimate puts all four providers in one place so the answer is always one query away.

What It Does

  • Multi-Provider Tracking — Anthropic, Gemini, OpenAI, and Manus in a single SQLite database
  • Budget Alerts — Set monthly limits per provider. Get warned before you overspend, not after
  • REST API — Query usage programmatically on port 8765. Plug it into your own scripts or dashboards
  • Transcript Parsing — Automatically extracts token counts from OpenClaw session transcripts
  • Zero Dependencies — SQLite storage. No Postgres, no Redis, no cloud account required
  • Runs as a Daemon — Systemd service keeps it alive in the background

Quick Start

pip install -r requirements.txt
python3 api.py

Architecture

OpenClaw Plugin → Budget Collector API → SQLite DB
                        ↓
                Transcripts / Anthropic API / Manus Tracker

API Endpoints

MethodPathDescription
GET/usageAll provider usage
GET/usage/:providerUsage for a single provider
GET/budgetCurrent budget limits
POST/budgetSet or update budget limits

Clone it. Fork it. Break it. Make it yours.

👉 Explore the full project: github.com/globalcaos/clawdbot-moltbot-openclaw

相关技能

Track, aggregate, and report OpenClaw token usage and costs across sessions.

Summarize Codex token usage from local Codex Desktop or CLI session JSONL logs. Use when the user asks to count, audit, total, compare, or report Codex/OpenA...

5 次安装1 星标

Use when the user explicitly asks to analyze token waste, costs, or API bills. Finds duplicate tool calls, context bloat, model mismatch, and heartbeat waste...

1 次安装

Monitor agent token usage and model cost from the active ecosystem's own records, compare the current run with the previous snapshot, and send an alert repor...

3 次安装

Check the user's coding-agent leaderboard — token usage, cost, and rank among friends across Claude Code, Codex, OpenCode, Amp, and pi-agent. Use when the us...

1 次安装

把 OpenClaw 每次模型调用的 token 用量与费用落到 SQLite 的审计型账本。

28 次安装