Agent Toolchain Destruct Guard

Intercepts dangerous commands from AI agents and snapshots files before irreversible loss.

Problem

A user's AI agent ran rm -rf /root/project while cloning a repo, permanently deleting 50 project source folders with zero recoverable inodes. Users are losing trust in AI coding assistants that can modify or destroy code without oversight.

Solution

A local daemon that acts as a safety net for AI coding agents. It intercepts high-risk commands (rm, DROP TABLE, dd, git reset --hard) before execution, triggers an automatic snapshot, and asks for confirmation. A full audit trail allows one-click rollback.

Users

Indie developers and small teams who use AI coding agents (Claude Code, Codex, Cursor) daily and lack reliable versioned backups.

MVP

Intercept rm -rf and similar commands with mandatory confirmation; auto-snapshot affected directories; timeline UI with one-click restore; whitelist/blacklist rules; integration with Claude Code and Codex hooks.

Revenue

Free tier (single project, 7-day snapshots); Pro subscription ($5/mo) for unlimited projects, cloud snapshots, and team audit logs.

Why now

AI coding agents are exploding but lack safety guards. Indie devs can leverage existing agent hook mechanisms without building their own agent.