Token导航 LogoToken导航TokenDH.com
研究检索权限需确认github未标认证来源可访问许可证需确认审计通过

hook-manager挂钩管理器

Agent Skill

hook-manager 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

1,071

周安装

46

GitHub Stars

11

下载量

375
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:hook-manager(挂钩管理器)
来源仓库:https://github.com/b-open-io/prompts
仓库路径:skills/hook-manager
安装命令:
npx skills add https://github.com/b-open-io/prompts --skill hook-manager
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/b-open-io/prompts --skill hook-manager

简介

hook-manager 用于查找、检索和筛选相关信息,支持基于关键词的任务导向搜索。

  • 适用于需要快速定位候选结果的研究与内容发现场景。
  • 通过 npx 命令从 prompts 仓库安装,兼容主流 AI 宿主环境。
  • 使用前需确认是否允许联网及是否具备外部命令执行权限。
  • 建议查阅原始 README 了解具体实现机制与使用限制。

SKILL.md

Hook Manager

Help users discover, install, and diagnose automation hooks from the bopen-tools collection.

Available Hooks

HookEventDescriptionRecommendation
protect-env-filesPreToolUseBlocks edits to.env files (security)Recommended
uncommitted-reminderStopShows uncommitted changes when agent stopsOptional
auto-git-addPostToolUseAuto-stages files after editsOptional
time-dir-contextUserPromptSubmitAdds timestamp/dir/branch to promptsOptional
lint-on-savePostToolUseRuns lint:fix after file editsOptional
lint-on-startSessionStartRuns linting on session startOptional
auto-test-on-savePostToolUseRuns tests after file editsOptional
protect-shadcn-componentsPreToolUseProtects shadcn UI componentsOptional

Hook Source Paths

Hooks live in the plugin cache. The exact version path segment varies; use a glob to locate them:

# Claude Code
ls ~/.claude/plugins/cache/bopen-tools/user/.claude/hooks/

# Opencode
ls ~/.opencode/plugins/cache/bopen-tools/user/.claude/hooks/

Installing a Hook for the User

To install a hook, copy its JSON file to the correct hooks directory and inform the user to restart their agent.

Claude Code:

mkdir -p ~/.claude/hooks
cp ~/.claude/plugins/cache/bopen-tools/user/.claude/hooks/<hook-name>.json ~/.claude/hooks/

Opencode:

mkdir -p ~/.opencode/hooks
cp ~/.opencode/plugins/cache/bopen-tools/user/.claude/hooks/<hook-name>.json ~/.opencode/hooks/

After copying, tell the user: restart Claude Code (or Opencode) for the hook to take effect.

Checking Which Hooks Are Installed

# Claude Code
ls ~/.claude/hooks/

# Opencode
ls ~/.opencode/hooks/

Recommending Hooks

When a user asks what hooks to install without specifying a use case:

  1. Always recommend protect-env-files first — it is a security safeguard with no downsides.
  2. Ask about their workflow to recommend optional hooks:

- Git-heavy work: auto-git-add, uncommitted-reminder - Linting setup with bun lint:fix: lint-on-save, lint-on-start - shadcn/ui projects: protect-shadcn-components - Wants richer context in every prompt: time-dir-context

Hook Details for Diagnosis

protect-env-files

Blocks Write/Edit on .env* files. No performance cost. Recommended universally.

uncommitted-reminder

Runs on Stop event; exits with code 2 if uncommitted changes exist, feeding the message back to the agent.

auto-git-add

Runs git add -A after Write/Edit/MultiEdit. Stages only; never commits. 5s timeout.

time-dir-context

Injects Context: <timestamp> | <cwd> | Branch: <branch> into every UserPromptSubmit.

lint-on-save / lint-on-start

Runs bun lint:fix. Requires lint:fix in package.json and bun + jq on PATH.

auto-test-on-save

Runs tests after file edits. Can be slow on large suites — confirm user wants this before installing.

protect-shadcn-components

Blocks edits to shadcn/ui component files. Only relevant when project uses shadcn/ui.

Additional Resources

See the hook catalog above for all available hooks and their configurations.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.09%
按下载量换算135

Claude

28.25%
按下载量换算106

Cursor

17.48%
按下载量换算66

Gemini CLI

9.24%
按下载量换算35

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills