mrexodia

Agent Cost Dashboard — Development skill for Claude Code

Development community

Interactive web dashboard to monitor and analyze your coding agent API costs.

How to install Agent Cost Dashboard

This entry records only its repository, not the path inside it, so there is no exact command to give. Open mrexodia/agent-cost-dashboard and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Agent Cost Dashboard does

Interactive web dashboard to monitor and analyze your coding agent API costs.

Alternatives in Development

Claude Code Viewer — A full-featured web-based Claude Code client that provides complete interactive functionality for managing Cla 984 ★
Claude Balancer — A load balancer proxy for multiple Claude OAuth accounts with automatic failover, request tracking, and web da 910 ★
Claude Usage — A local dashboard for tracking your Claude Code token usage, costs, and session history 864 ★

README

Agent Cost Dashboard

Web dashboard to monitor API costs for [Pi](https://github.com/mariozechner/pi-coding-agent), [Oh My Pi](https://github.com/can1357/oh-my-pi), [Claude Code](https://github.com/anthropics/claude-code), [Codex CLI](https://github.com/openai/codex), and [Gemini CLI](https://github.com/google-gemini/gemini-cli) coding agents.

No external dependencies — pure Python stdlib.

![Main dashboard showing global stats, and daily spending](screenshots/dashboard-overview.png)

Features

Global Statistics

Track total spending across all projects and sessions:

Total tokens broken down by input, output, cache-read, cache-write, and reasoning counts when exposed
Detailed token usage across all models where source data exposes it
Session count and project count
LLM time vs tool execution time
Average tokens per second across all API calls

Daily Spending Chart

Timeline of API costs over time.

Model Breakdown

Costs broken down by AI model (Claude, Gemini, GPT-5, O3, O4, GLM, etc.):

Messages, input/output/cache-read/cache-write/reasoning token usage, and cost per model
Average tokens per second

![Model Stats](screenshots/model-stats.png)

Tool Usage

Track which tools your agent uses most:

Call counts and execution time per tool
Error rates

![Tool Stats](screenshots/tool-stats.png)

Project View

All projects with expandable details:

Per-project cost, model usage, tool usage, and session history
Sortable by cost, tokens, LLM time, or date

![Projects](screenshots/projects.png)

Session Browser

Browse every session with full details:

Copy command to resume session to the clipboard
Full transcript export (Pi via pi --export, Claude and Codex via built-in exporters)
Session duration, LLM time, and tool time
Subagent session support with expandable grouping
Sortable by date, duration, cost, tokens, and more

![Sessions](screenshots/sessions.png)