mikehasa

Agentacct — Productivity skill for Claude Code

Productivity community

See what your coding agents did and what it cost.

How to install Agentacct

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

What Agentacct does

See what your coding agents did and what it cost. Breaks each task down into work steps — tools used, files changed, tests run, time and tokens spent. Local-first dashboard for Claude Code, Codex, OpenCode, and more. No login, no telemetry.

Alternatives in Productivity

Costs — Show cost breakdown by provider and workflow for the current session 2.8k ★
Tradingview MCP — Real-time crypto & stock screening, advanced technical indicators, Bollinger Bands intelligence, candlestick p 2.6k ★
Cc Lens — A real-time monitoring dashboard for Claude Code 440 ★

README

agentacct

[![tests](https://github.com/mikehasa/agentacct/actions/workflows/tests.yml/badge.svg)](https://github.com/mikehasa/agentacct/actions/workflows/tests.yml) [![PyPI](https://img.shields.io/pypi/v/agentacct.svg)](https://pypi.org/project/agentacct/) [![Python](https://img.shields.io/pypi/pyversions/agentacct.svg)](https://pypi.org/project/agentacct/) [![License: MIT](https://img.shields.io/badge/license-MIT-yellow.svg)](LICENSE)

**See what your coding agents actually did — and whether you can trust it — across Claude Code, Codex, OpenCode, and Hermes, without any of it leaving your machine.**

agentacct is local-first Agent Work Intelligence for coding agents. It reads the session logs your agents already write on disk — Claude Code, Codex, OpenCode, and Hermes — joins them with the work each session records as it goes, and turns the result into one honest **Work Receipt** per task: what it did (the commands it ran, the files it touched, the tools it used), what it cost, and how well that is actually proven. Each receipt reads like an audit record, not a vibe: the decision ("the agent says it's done") and the evidence ("a machine check proves it") are separate axes, and every evidence tier has its own shape — an agent's claim can never dress up as verification. See it in the **macOS app**, a live terminal dashboard (**`agentacct tui`**), or over a local JSON API. No browser tab, no hosted server, no account.

![A Work Receipt in the macOS app — a Verified task with its summary strip (actions, estimated cost, elapsed, 4/4 checks passed), the receipt dimensions ledger with per-field provenance chips, the live checks with exit codes, and the evidence-coverage card](https://raw.githubusercontent.com/mikehasa/agentacct/main/docs/assets/app-work-receipt.png)

**Private by design.** Everything stays on your machine: state is plain local files, the only listener is a loopback-only local JSON API (`127.0.0.1`) that onboarding starts and `agentacct stop` stops, and