Skip to main content

Coolhand and your coding agents

How Coolhand ingests Claude Code, Claude Cowork, and GitHub Copilot sessions, and what each transcript format can and cannot tell you.

  • Claude Code best practices

    Coolhand ingests Claude Code sessions from the transcripts saved on disk, not by intercepting API calls in real time. Latency and temperature are never present because the transcript format does not record them; prompts, responses, token counts, and tool use are all captured once a session ends.

  • Claude Cowork best practices

    Claude Cowork logs are ingested the same way as Claude Code: from locally saved session transcripts rather than live API interception. The same constraints apply, so latency and temperature are always blank, while prompts, responses, and token counts arrive in full once a session ends.

  • GitHub Copilot best practices

    GitHub Copilot emits two different response payload shapes, and which one you get determines how much token detail Coolhand can record. The newer shape carries `copilotUsage.tokenDetails`; the older one omits several fields, so some cost figures are estimates rather than reported values.