Cc Safe Setup
Marketplace Warning ActiveSafety hooks for Claude Code — 734 battle-tested hooks from 800+ hours of autonomous operation. Prevents rm -rf, force-push, credential leaks, unauthorized fund transfers, deny-rules bypass, and more.
To provide essential safety guards for Claude Code, preventing catastrophic data loss, security breaches, and operational errors during autonomous AI coding sessions.
Features
- Prevents destructive file operations (rm -rf, Remove-Item)
- Blocks dangerous Git commands (force-push, hard-reset)
- Catches credential leaks (e.g., .env files)
- Validates syntax after edits
- Monitors context window to prevent session state loss
Use Cases
- Use when running Claude Code in autonomous or semi-autonomous modes to prevent accidental data loss.
- Use to protect sensitive credentials and API keys from being committed or leaked.
- Use to ensure code integrity by validating syntax before commands are executed.
- Use to prevent unauthorized changes to main branches or shared repositories.
Non-Goals
- Does not directly interact with external services beyond the Claude Code environment.
- Does not replace the need for careful prompt engineering or CLAUDE.md rules.
- Does not offer AI code generation or debugging capabilities; focuses solely on operational safety.
Practices
- Security hardening
- Operational safety
- Defensive programming
Prerequisites
- Claude Code environment
- jq (installed via package manager, e.g., `brew install jq` or `apt install jq`)
Security
- critical:Unguarded Destructive OperationsThe core purpose of the extension is to guard against destructive operations like 'rm -rf', 'force-push', and others, directly preventing unguarded destructive actions.
Installation
/plugin marketplace add yurukusa/cc-safe-setupContains 4 extensions
Plugin (4)
5 essential safety hooks for Claude Code. Blocks rm -rf, force-push, hard-reset, .env overwrites, and package publish. The minimum viable safety net from 800+ hours of autonomous operation.
Git safety hooks for Claude Code. Blocks force-push, protects main/master branch, prevents hard-reset, guards interactive rebase, and blocks git clean -fd.
Protect secrets and credentials from Claude Code. Blocks writes to .env files, detects API keys in shell commands, prevents hardcoded tokens, and guards service account JSON files.
Token consumption guards for Claude Code. Warns on large file reads (100KB+), limits unique file reads per session, estimates token budget, and caps subagent spawns. From 800+ hours of autonomous operation data.
Quality Score
WarningTrust Signals
Similar Extensions
Cozempic
1002x the effective context with smart weight-loss for Claude Code — prune bloated sessions, protect agent teams from compaction, monitor token usage with MCP tools
Caveman Repo
100🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Cortex Plugins
100Persistent memory and cognitive profiling plugins for Claude Code
Claude Code Hooks Marketplace
95Production safety hooks for autonomous Claude Code operation