Track long-horizon objectives across multiple sessions with milestone checkpoints, progress persistence, and drift detection
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-horizon-track-2caa53a9685b ,按照其中的说明把「horizon-track」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
Track long-running objectives that span multiple sessions, days, or weeks.
When an objective is too large for a single session — multi-week features, research programs, migration projects, or any work that requires persistent progress tracking across conversations.
mcp__plugin_ruflo-core_ruflo__memory_store with namespace horizons and key horizon-[name]:
{
"objective": "...",
"created": "2026-04-28",
"targetDate": "2026-05-15",
"milestones": [
{"id": "m1", "name": "...", "criteria": "...", "status": "pending"},
{"id": "m2", "name": "...", "criteria": "...", "status": "pending"}
],
"currentMilestone": "m1",
"sessions": []
}
mcp__plugin_ruflo-core_ruflo__memory_retrieve key horizon-[name] namespace horizonsmcp__plugin_ruflo-core_ruflo__hooks_intelligence_pattern-storehorizons — active horizon definitions and statehorizon-sessions — per-session summaries keyed by [horizon]-[date]horizon-learnings — patterns and insights discovered during the horizon