claude-code-hooks

Purpose: Preventing unsafe or unwanted Claude Code actions while adding custom checks and automation to the agent loop.

Inferred · not functionally tested

Audience: developers using Claude Code

Inferred · not functionally tested

Functions: agents, workflow_automation

Inferred · not functionally tested

Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: hooks.karanbansal.in · github.com. These links do not verify the individual claims.

In the AI security & guardrails space, claude-code-hooks takes a focused approach. Inferred · not functionally tested: It focuses on preventing unsafe or unwanted Claude Code actions while adding custom checks and automation to the agent loop. Inferred · not functionally tested: claude-code-hooks is an open-source project aimed at developers using Claude Code. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: It ships for the command line, and it can be self-hosted.

It is developed by Karan Bansal (India), and it first shipped in 2026. The project is developed in the open on GitHub with 475 stars and 22 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include lifecycle hooks, command blocking, and secret protection.

Summary written by a language model from the project’s public pages.