redhat-community-ai-tools

Spenda — AI skill for Claude Code

AI community

Spenda - Local usage and cost tracking for coding agents.

How to install Spenda

This entry records only its repository, not the path inside it, so there is no exact command to give. Open redhat-community-ai-tools/spenda and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Spenda does

Spenda - Local usage and cost tracking for coding agents. It is a local, privacy-first tracker for AI coding agents. It monitors token usage and API costs in real time. Get granular breakdowns by project, model, and task to spot inefficiencies, optimize your budget, and keep your data completely secure.

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 ★
Manifest — Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage 4.1k ★
Claude Usage Tracker — Native macOS menu bar app for tracking Claude AI usage limits in real-time 2.2k ★

README

Spenda

A local dashboard for token usage, costs, models, projects, and session activity from Codex, OpenCode, Claude Code, and Cursor.

![Dashboard overview](docs/screenshots/overview.png)

What you can see

Spend, token, and call trends
Model composition and cache usage
Sessions, subagents, projects, and source-specific reports
CSV and JSON exports
Light and dark themes

The dashboard reads local history and stores its own reporting database. It does not send source data to an external service.

Install

Requires Python 3.11 or newer and at least one supported coding agent with local history.

With uv

uv sync
uv run spenda ingest --all
uv run spenda serve

With pip

python -m venv .venv
source .venv/bin/activate
python -m pip install -r requirements.txt
python -m pip install .
spenda ingest --all
spenda serve

Without cloning

You can also install Spenda directly from GitHub, without cloning the repo first.

pip install git+https://github.com/sshnaidm/spenda.git

Or with [pipx](https://pypa.github.io/pipx/) (recommended, isolates the CLI in its own venv):

pipx install git+https://github.com/sshnaidm/spenda.git

Or with uv:

uv tool install git+https://github.com/sshnaidm/spenda.git

Then run `spenda ingest --all` and `spenda serve` as above.

You can also run it directly with `uvx`, without installing anything:

uvx git+https://github.com/sshnaidm/spenda ingest --all
uvx git+https://github.com/sshnaidm/spenda serve

Open .

Use

Start the dashboard with `spenda serve`. If you installed with uv, use `uv run spenda serve`. It checks configured sources for updates while it runs. Use `spenda doctor` to see which sources it found and why a source may show no data.

Choose **All sources**, **Codex**, **OpenCode**, **Claude Code**, or **Cursor** from the dashboard filter. The Sessions view lets you inspect individual sessions; Models and Proje