Set, show, or advance the per-session agent-launcher goal (./my-agent/goal.json) — the through-line of a CMA launch. Backs the opt-in SessionStart hook. Subcomm
复制下面这句话,粘贴给 Claude Code、Codex、Cursor 等 AI 编程工具,它会读取安装说明并在你确认后完成安装。
请阅读 https://ai.atlankj.com/install/asset/gh-claude-skills-a38d0ff01cef ,按照其中的说明把「cs-goal」安装到你(当前 AI 工具)中。执行前先告诉我将运行的命令和写入的位置,等我确认。
查看 AI 将读取的安装说明正在读取 GitHub 原文…
内容来自 GitHub 原始文件,由原作者维护。在 GitHub 查看
The goal is one sentence for one agent. It selects the phase and the loop shape.
$ARGUMENTS
Run goal_state.py under agent-launcher/skills/agent-launcher-orchestrator/scripts/:
set "<goal>" → goal_state.py init --goal "<goal>" (or set --goal if it exists).status → goal_state.py status (prints goal, agent_name, phase, phases_done, loop).advance → goal_state.py advance (moves to the next phase).phase <name> → goal_state.py set --phase <name> (interview | stage-launch |
grade-iterate | run-without-you | wrap-up | done).Enable auto-surfacing each session with export AGENT_LAUNCHER_SESSION=1 (the
opt-in SessionStart hook). Two jobs → two goals in two ./my-agent-*/ folders.