claude

safety-hooks

Provides safety guards to block or require confirmation for risky CLI operations (e.g., rm, destructive git actions, .env access, large file operations)

2,034 on GitHubby Prasad Chalasaniv1.15.2MITupdated 2 days ago
/

Plugin safety-hooks from marketplace cctools-plugins in pchalasani/claude-code-tools. Commands read from the repo's manifest — 2 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Hooks (5)

  • PreToolUse

    bash -c 'if test -f "${CLAUDE_PLUGIN_ROOT}/hooks/bash_hook.py"; then python3 "${CLAUDE_PLUGIN_ROOT}/hooks/bash_hook.py"; else echo "{\"decision\":\"approve\"}"; fi'

  • PreToolUse

    bash -c 'if test -f "${CLAUDE_PLUGIN_ROOT}/hooks/file_length_limit_hook.py"; then python3 "${CLAUDE_PLUGIN_ROOT}/hooks/file_length_limit_hook.py"; else echo "{\"decision\":\"approve\"}"; fi'

  • PreToolUse

    bash -c 'if test -f "${CLAUDE_PLUGIN_ROOT}/hooks/file_length_limit_hook.py"; then python3 "${CLAUDE_PLUGIN_ROOT}/hooks/file_length_limit_hook.py"; else echo "{\"decision\":\"approve\"}"; fi'

  • PreToolUse

    bash -c 'if test -f "${CLAUDE_PLUGIN_ROOT}/hooks/read_env_protection_hook.py"; then python3 "${CLAUDE_PLUGIN_ROOT}/hooks/read_env_protection_hook.py"; else echo "{\"decision\":\"approve\"}"; fi'

  • UserPromptSubmit

    bash -c 'if test -f "${CLAUDE_PLUGIN_ROOT}/hooks/allow_git_hook.py"; then python3 "${CLAUDE_PLUGIN_ROOT}/hooks/allow_git_hook.py"; else echo "{\"decision\":\"approve\"}"; fi'

View source on GitHub

More from pchalasani/claude-code-tools

All 12 plugins →

aichat

claude

Adds `aichat`-related capabilities (agent support, reusable skills, hooks, and a slash command) for continuing work in CLI agent sessions without compaction, and for searching sessions

2 skills · 1 command · 1 agent · hooks

2,034

workflow

claude

Workflow utilities and agents including code walkthrough tools, work logging, issue specification helpers, and a UI testing agent for browser-based validation

4 skills · 1 agent

2,034

msg

claudecodex

Inter-agent communication for Claude Code and Codex CLI sessions via threads and messages

1 skill · 2 commands · hooks

2,034

writing

claudecodex

Prose-quality skills: agent-style (21 literature-backed rules for formal technical prose) and remove-ai-patterns (de-AI text using the avoid-ai-writing catalog plus a deterministic detector)

4 skills

2,034

voice

claude

Audio feedback when Claude Code agent completes tasks using pocket-tts

1 skill · 1 command · hooks

2,034

dynamic-workflow

claudecodex

Durable JavaScript orchestration for headless Codex agents, plus the github-wake skill

2 skills

2,034

Maintain safety-hooks?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins12 plugins