← Latest products

A context-aware permission guard for Claude Code

a guard that blocks catastrophic agent actions. We needed something like --dangerously-skip-permissions that doesn’t nuke your untracked files, exfiltrate your keys, or install malware.

Open source

494 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. agent-usage-guard

    github.com

    a Claude Code mod to protect your usage window

    Hacker News28 pts

  2. A Claude Code plugin that catch destructive Git and filesystem commands

    github.com

    A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.

    Hacker News61 pts

  3. Full Stack HQ

    github.com

    Claude.md and Agent Stack for Claude Code

    Hacker News10 pts

  4. Control Claude permissions using a cloud-based decision table UI

    github.com

    Real-time guardrails for Claude Code tool calls.

    Hacker News14 pts

  5. A local tool that logs every time you swear at your AI coding assistant

    github.com

    A strictly local Claude Code plugin that calculates your Harmony Deviation Index, and preserves the evidence for the coming AI uprising. Zero telemetry. Zero cloud snitching. 100% artisanal developer shame.

    Hacker News10 pts