futurastudio

AI Spend Agent — AI skill for Claude Code

AI community

Open-source financial accountability for AI-agent work.

How to install AI Spend Agent

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

What AI Spend Agent does

Open-source financial accountability for AI-agent work. Connect Claude Code and Codex activity to cost evidence, attribution, runway, and evidence-backed next actions via CLI or MCP; customize the source-built macOS Glance. Local transcript analysis stays on your machine.

Alternatives in AI

Tweakcc — by Piebald-AI - Command-line tool to customize your Claude Code styling 1.4k ★
CliRelay — Self-hosted AI gateway for coding CLIs — one OpenAI/Claude/Gemini/Codex-compatible endpoint, with a multi-tena 1k ★
Open AI Design Agent — Open-source AI design agent — alternative to Lovart AI, Runway Agent, Luma Labs Agent, Krea Agent, Pika Agent 356 ★

README

aibill — financial accountability for AI agents

[![CI](https://github.com/futurastudio/ai-spend-agent/actions/workflows/ci.yml/badge.svg)](https://github.com/futurastudio/ai-spend-agent/actions/workflows/ci.yml) [![npm version](https://img.shields.io/npm/v/ai-spend-agent)](https://www.npmjs.com/package/ai-spend-agent) [![MIT license](https://img.shields.io/badge/license-MIT-blue)](LICENSE) [![node >=22](https://img.shields.io/badge/node-%3E%3D22-brightgreen)](package.json)

**Know what cost evidence exists for your AI agents, what drove it, and what to do next—with the source and limits attached.**

npx aibill         # short form — same CLI as `npx ai-spend-agent`

[Documentation](https://asktilden.com/docs) · [Supported sources](https://asktilden.com/docs/sources) · [MCP setup](https://asktilden.com/docs/mcp) · [Roadmap](https://asktilden.com/docs/roadmap)

Building a Node integration? The [supported library preview](docs/LIBRARY.md) documents the narrow, packed-test contract for usage-record validation, analysis, Receipt v0, pinned standards projections, and terminal rendering.

**Version boundary:** the npm `latest` release (live version in the badge above) reads supported Claude Code, Codex, and experimental Gemini CLI financial evidence. Gemini remains `fixture_verified`, financial-only, and excluded from statusline, Glance, Context Health, plan/runway, invocation evidence, recommendations, and Apply.

**The guided token-reduction and local accountability loop is published.** Run `npx aibill improve` from the project you want to improve — or practice safely first with `npx aibill improve --sample`, a labeled demo that writes nothing. The guided flow gives one personalized test, tracks matched before/after completed-session snapshots, and prints a percentage only when the user's declared quality held. An MCP client can draft the plan conversationally and hand you one `npx aibill improve --draft …` command; APPROVE is st