# Track Coding-Agent Work Evidence With agentacct

> Create a local dashboard that joins coding-agent session logs, token estimates, recorded work steps, and verification checks into reviewable task evidence.

- Skill: `agentskillexchange/track-coding-agent-work-evidence-with-agentacct` (Agent Skill)
- Install (CLI): `npx skillmds@latest add agentskillexchange/track-coding-agent-work-evidence-with-agentacct`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/track-coding-agent-work-evidence-with-agentacct/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/agentskillexchange/track-coding-agent-work-evidence-with-agentacct

---


# Track Coding-Agent Work Evidence With agentacct

Create a local dashboard that joins coding-agent session logs, token estimates, recorded work steps, and verification checks into reviewable task evidence.

## Prerequisites

Python 3.11 or newer; agentacct CLI; local coding-agent session logs; optional MCP tools/hooks installed by onboarding

## Installation

Install or set up from the source-backed instructions:

Install with pipx install agentacct, then run agentacct onboard. The README also documents uv tool install agentacct and venv fallback options.

- Source: https://github.com/mikehasa/agentacct

## Documentation

- https://github.com/mikehasa/agentacct/blob/main/docs/reference.md

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/track-coding-agent-work-evidence-with-agentacct/)