AI Employees. Free to hire.

• Claude Code

  Ready

  Native format. Leave the kit where you extracted it and register each routine as a scheduled task pointed at its folder. Do not copy them into ~/.claude/skills: they are scheduled work, not on-demand skills.

• OpenClaw

  Ready

  Reads the same SKILL.md format. Register each routine's schedule as an OpenClaw cron job pointed at the kit's routines folder.

• Hermes

  Ready

  Point Hermes's recurring jobs at the kit's routines folder and mirror the cadence in SCHEDULE.md, one job per routine.

• OpenCode

  Ready

  Reads the Claude Code skill format directly. Mirror the schedule table into its recurring runs, one run per routine folder.

• Grok Bot

  Ready

  The closest native fit, and the one harness whose computer is not yours. Every bot on your account shares one cloud computer, so the bot installs the kit there itself, you paste the kit's AGENTS.md into the bot's Instructions field, and one recurring task per routine runs from SCHEDULE.md. Your sessions reach that browser only through a cookie sync you run, and every bot then shares every login. The morning brief is posted into the bot's own thread, because you never open that computer's files.

• Codex

  Ready

  Drive the cadence with Codex scheduled runs, one job per routine, each handed its routine's SKILL.md as the run prompt.

• Antigravity

  Ready

  Schedule each routine with the agy job runner, pointed at the routine folder rather than registered as a global pack.

• Pi

  Ready

  Reads skills folders directly and runs headless with pi -p. No scheduler of its own: mirror the schedule table into the operating system's scheduler, one job per routine, with the kit folder as the working directory.

• Cline

  Ready

  The Cline CLI has its own cron. Register one scheduled task per routine with cline schedule create, handed that routine's SKILL.md as the prompt, with auto approve on so a run never hangs.

• Qwen Code

  Ready

  Reads the skill format and ships scheduled tasks. Register one per routine, or drive qwen -p from the operating system's scheduler, one run per routine folder.

• DeepSeek

  Ready

  dsh runs a local server and scheduling is one of its plugins. Register one scheduled run per routine, handed that routine's SKILL.md as the prompt, with the kit folder as the working directory.

• Muse

  Ready

  Meta's Muse Code reads the Claude Code skill format directly and imports it with one command. Its own scheduled jobs stop when the terminal closes, so mirror the schedule table into the operating system's scheduler, one job per routine, each running muse exec with approvals disabled and the routine's SKILL.md as the prompt. Muse itself, the personal agent, runs on Meta's cloud computer with connectors, skills and crons, the Grok Bot shape; whether it can reach your signed in accounts is the first thing to check.

• Dots

  Ready

  OpenAI's always on agents, announced September 29, 2026: each dot has its own cloud computer and browser and reaches you in ChatGPT, Slack and Teams, so it is the Grok Bot shape inside ChatGPT. Give your dot the kit and hand it each routine's SKILL.md as the task, one task per routine on the schedule SCHEDULE.md names. Connect accounts through its plugins, open its computer to read the first run, and check that it keeps the kit folder between runs. Its background research uses read only tools, and sensitive actions such as changing a password always stay with you.

They drive your browser and your PC the way you do, on the harness you already run. Every run makes the next one better, and how much each one does on its own is yours to set.