secret-warn

Official

Catch secrets in real time, before exposure.

Authormycelium-hq
Version1.0.0
Installs0

System Documentation

What problem does it solve?

secret-warn provides real-time guardrails that detect secrets, sensitive patterns, and unsafe shell constructs the moment they appear in Claude Code tool-calls, preventing leaks before they land in drafts or CI.

Core Features & Use Cases

  • Real-time detection of API keys, private keys, and high-entropy strings in edit-time and shell commands.
  • PreToolUse and PostToolUse hooks plus a Bash guard to enforce safety across Claude Code workflows.
  • Maintains a base64-encoded registry of 11+ rules with allowlist and bypass options for controlled environments, plus an audit log for traceability.
  • Use case: during code review or drafting, it blocks or warns on secret exposures and unsafe commands, ensuring secure development sessions.

Quick Start

Run the installer to activate secret-warn in Claude Code and then run the quick_test.sh script to verify installation.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: secret-warn
Download link: https://github.com/mycelium-hq/ai-brain-starter/archive/main.zip#secret-warn

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.