Cc Safe Setup
Plugin Verified Active734 safety hooks for Claude Code — prevent file deletion, credential leaks, git disasters, and token waste during autonomous AI coding sessions
To significantly enhance the safety and reliability of autonomous AI coding sessions by preventing common and catastrophic errors.
Features
- Prevents file deletion and overwrites
- Blocks credential leaks and insecure commands
- Protects against git disasters
- Optimizes token usage
- Provides real-time command blocking and alerts
Use Cases
- Protecting production environments from accidental AI modifications
- Preventing sensitive data from being leaked or committed insecurely
- Ensuring AI-driven code changes are safe and predictable
- Mitigating risks during autonomous coding sessions
Non-Goals
- Replacing AI's core decision-making or coding capabilities
- Providing AI with new coding functionalities
- Acting as a primary code linter or formatter
Prerequisites
- jq installed on the system
Scope
- info:Tool surface sizeWhile the README lists 734 hooks and many commands, the core plugin functionality is delivered through a few main commands and a set of integrated hooks, keeping the primary surface manageable.
Installation
/plugin install cc-safe-setup@yurukusa-cc-safe-setupQuality Score
VerifiedTrust Signals
Similar Extensions
Claude Code Hooks
99Production safety hooks for autonomous Claude Code operation. Context monitoring, syntax checking, branch protection, activity logging, and more.
Hooks Safety
99Essential safety hooks to prevent destructive operations in Claude Code. From cc-safe-setup (655+ hooks).
Karpathy Coder
100Active coding discipline enforcer based on Karpathy's 4 principles: surface assumptions, keep it simple, make surgical changes, define verifiable goals. Ships 4 Python tools (complexity_checker, diff_surgeon, assumption_linter, goal_verifier), a review agent, /karpathy-check slash command, and a pre-commit hook. All tools stdlib-only.
Autoresearch Agent
100Autonomous experiment loop that optimizes any file by a measurable metric. 5 slash commands, 8 evaluators, configurable loop intervals (10min to monthly).
Tdd
99TDD workflow enforcement with auto-test hook
Claude Recap
99Topic-based automatic memory for Claude Code — never lose context across sessions or compactions.