mikehasa/agentacct：README 來源編輯指南

mikehasa/agentacct 的 README 將專案描述為「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.」。本文只整理倉庫可直接核對的內容，不把 star、Fork 或宣傳語當成品質證明。README 在「agentacct」下寫到：See what your coding agents actually did , and what it cost , in a live terminal dashboard that never leaves your machine.。這說明的是專案邊界，不是已完成的生產驗證。

從 README 的「What you get」與相關條目，可以先判斷它是否處理你的實際問題：The work, not just the tokens. Every session rolls up its recorded work steps and machine checks , a passing test is Verified evidence, an agent's own claim stays labeled Agent reported.。若需求不同，不應只因專案熱度就採用。本文保留原始專案名、命令與元件名，方便回到一手來源核對。 README 另外列出一項可核對的資訊：Honest usage and cost. Tokens per agent, model, and day , read from the clients' own local session files and labeled clientreported; costs are clearly marked pricing-table estimates, never invoices.。這類原文條目可用來設計試跑步驟，但不能取代實際環境測試。

README 將運作方式分散在「agentacct」等段落。可確認的線索包括：Private by design. Everything stays on your machine: state is plain local files, nothing binds a network port, and there is no phone-home telemetry, no account, no cloud sync. agentacct never stores or requests a provider API key.。本文不把未寫出的架構、效能或安全邊界補成結論；真正的執行鏈仍要配合目錄、設定檔與版本標籤檢查。

第一次安裝應從 README 指出的入口開始。目前可核對的命令是： Install and set up agentacct , a local-first dashboard that reads my coding-agent logs read-only and shows honest token usage and cost. Run `pipx install agentacct` (or `pipx install git+https://github.com/mikehasa/agentacct`), then `agentacct onboard` (installs once per machine, global by default, zero files written into the repo), then tell me the dashboard URL. Observe-only: never store, request, or echo any API key; all state stays local on this machine. Don't modify my global client confi 如果倉庫沒有命令，本文不會自行編造步驟，而是建議先閱讀「What you get」，確認系統依賴、預設埠與首次初始化。