Installation
npx skills add b-open-io/prompts --skill hook-manager 46
Installs
Hook Manager
Help users discover, install, and diagnose automation hooks from the bopen-tools collection.
Available Hooks
| Hook | Event | Description | Recommendation |
|---|---|---|---|
protect-env-files |
PreToolUse | Blocks edits to .env files (security) | Recommended |
uncommitted-reminder |
Stop | Shows uncommitted changes when agent stops | Optional |
auto-git-add |
PostToolUse | Auto-stages files after edits | Optional |
time-dir-context |
UserPromptSubmit | Adds timestamp/dir/branch to prompts | Optional |
lint-on-save |
PostToolUse | Runs lint:fix after file edits | Optional |
lint-on-start |
SessionStart | Runs linting on session start | Optional |
auto-test-on-save |
PostToolUse | Runs tests after file edits | Optional |
protect-shadcn-components |
PreToolUse | Protects shadcn UI components | Optional |
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:
- Always recommend
protect-env-filesfirst — it is a security safeguard with no downsides. - 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
- Git-heavy work:
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.
Installs
Security Audit
View Source
b-open-io/prompts
More from this source
EU-Hosted Inference API Power your AI Agents with
the best open-source models.
Drop-in OpenAI-compatible API. No data leaves Europe.
Explore Inference APIGLM
GLM 5
$1.00 / $3.20
per M tokens
Kimi
Kimi K2.5
$0.60 / $2.80
per M tokens
MiniMax
MiniMax M2.5
$0.30 / $1.20
per M tokens
Qwen
Qwen3.5 122B
$0.40 / $3.00
per M tokens
How to use this skill
Install hook-manager by running npx skills add b-open-io/prompts --skill hook-manager in your project directory. Run the install command above in your project directory. The skill file will be downloaded from GitHub and placed in your project.
No configuration needed. Your AI agent (Claude Code, Cursor, Windsurf, etc.) automatically detects installed skills and uses them as context when generating code.
The skill enhances your agent's understanding of hook-manager, helping it follow established patterns, avoid common mistakes, and produce production-ready output.
What you get
Skills are plain-text instruction files — not executable code. They encode expert knowledge about frameworks, languages, or tools that your AI agent reads to improve its output. This means zero runtime overhead, no dependency conflicts, and full transparency: you can read and review every instruction before installing.
Compatibility
This skill works with any AI coding agent that supports the skills.sh format, including Claude Code (Anthropic), Cursor, Windsurf, Cline, Aider, and other tools that read project-level context files. Skills are framework-agnostic at the transport level — the content inside determines which language or framework it applies to.
Made in Europe Chat with 100+ AI Models in one App.
Use Claude, ChatGPT, Gemini alongside with EU-Hosted Models like Deepseek, GLM-5, Kimi K2.5 and many more.
Get the App:
