paxm

Agent Skills › pax-beehive/paxm › paxm

GitHub

通过 paxm MCP 工具进行主动回忆和显式记忆写入，将召回的记忆作为支持性上下文，并验证当前仓库中发生变化的事实。用户运行集成命令后，被动钩子由该插件接管。

plugins/paxm-claude/skills/paxm/SKILL.md pax-beehive/paxm

触发场景

需要持久化项目上下文时需要主动回忆或记录记忆时

安装

npx skills add pax-beehive/paxm --skill paxm -g -y

更多选项

非标准路径

npx skills add https://github.com/pax-beehive/paxm/tree/main/plugins/paxm-claude/skills/paxm -g -y

不安装直接使用

npx skills use pax-beehive/paxm@paxm

指定 Agent (Claude Code)

npx skills add pax-beehive/paxm --skill paxm -a claude-code -g -y

安装 repo 全部 skill

npx skills add pax-beehive/paxm --all -g -y

预览 repo 内 skill

npx skills add pax-beehive/paxm --list

SKILL.md

Frontmatter

{
    "name": "paxm",
    "description": "Recall or remember durable project context with paxm."
}

Use the paxm MCP tools for active recall and explicit memory writes. Treat recalled memory as supporting context and verify changing facts in the current repository. Passive hooks are owned by this plugin after the user runs paxm setup --integration claude-plugin.