Name: AI for small businesses and freelancers
Availability: InStock

What are hooks?

Hooks let you intercept and react to Claude Code lifecycle events: before running a tool, after doing so, when Claude finishes a response, and so on.

Common use cases:

Automatically format code after each edit.
Log all Claude operations.
Block dangerous operations with custom logic.
Send notifications when Claude finishes a long task.
Run tests automatically after each change.

Hook types

Configuring hooks

Hooks are configured in .claude/settings.json (project) or ~/.claude/settings.json (global):

TerminalCode

{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Edit|Write",
        "hooks": [
          {
            "type": "command",
            "command": "prettier --write $CLAUDE_FILE_PATH"
          }
        ]
      }
    ],
    "Stop": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "osascript -e 'display notification "Claude terminó" with title "Claude Code"'"
          }
        ]
      }
    ]
  }
}

Environment variables available in hooks

The matcher

The matcher field is a regular expression matched against the tool name. If not specified, the hook applies to all tools.

TerminalCode

# Solo edición de archivos TypeScript
"matcher": "Edit"

# Herramientas de bash y edición
"matcher": "Bash|Edit|Write"

# Cualquier herramienta de lectura
"matcher": "^Read"

Command-type hooks

The most common type. Runs a shell command. The hook can read event information via environment variables or via stdin (JSON):

TerminalCode

{
  "type": "command",
  "command": "bash /ruta/a/mi-hook.sh",
  "timeout": 30
}

Example: hook that reads event data from stdin

TerminalCode

#!/bin/bash
# mi-hook.sh — recibe el evento completo como JSON por stdin
EVENT=$(cat)
TOOL=$(echo $EVENT | jq -r '.tool_name')
FILE=$(echo $EVENT | jq -r '.tool_input.path // ""')

echo "Herramienta: $TOOL, Archivo: $FILE" >> ~/.claude/hook.log

Blocking operations with PreToolUse

A PreToolUse hook can return a non-zero exit code to block the operation:

TerminalCode

#!/bin/bash
# Bloquear rm -rf
TOOL=$(cat | jq -r '.tool_name')
CMD=$(cat | jq -r '.tool_input.command // ""')

if [[ "$CMD" == *"rm -rf"* ]]; then
  echo "BLOQUEADO: rm -rf no permitido"
  exit 1  # exit 1 = bloquear la operación
fi

exit 0  # exit 0 = permitir

Configure it like this in settings.json:

TerminalCode

{
  "hooks": {
    "PreToolUse": [{
      "matcher": "Bash",
      "hooks": [{
        "type": "command",
        "command": "bash ~/.claude/hooks/bloquear-rm.sh"
      }]
    }]
  }
}

Practical examples

Format with Prettier after editing

TerminalCode

{
  "hooks": {
    "PostToolUse": [{
      "matcher": "Edit|Write",
      "hooks": [{
        "type": "command",
        "command": "npx prettier --write "$CLAUDE_FILE_PATH" 2>/dev/null || true"
      }]
    }]
  }
}

Run tests after changes

TerminalCode

{
  "hooks": {
    "Stop": [{
      "hooks": [{
        "type": "command",
        "command": "npm test --watchAll=false 2>&1 | tail -20"
      }]
    }]
  }
}

Log all operations

TerminalCode

{
  "hooks": {
    "PostToolUse": [{
      "hooks": [{
        "type": "command",
        "command": "echo "$(date) - $CLAUDE_TOOL_NAME: $CLAUDE_FILE_PATH" >> ~/.claude/audit.log"
      }]
    }]
  }
}

Managing hooks from the CLI

TerminalCode

# Ver hooks configurados (dentro de Claude Code)
/hooks

# O abre settings.json directamente:
claude config