git-safety

One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).

A cooperative gate for the shell commands AI agents run. Previews, backups, policy, audit. Claude Code + Cursor. A windshield, not a sandbox.

Active session guardian for non-technical contributors shipping AI-assisted code in shared codebases

Claude Code PreToolUse hook that blocks destructive shell commands before they execute

Codex skill that protects Git workspaces from large-file, VM image, generated-output, and .git/objects storage blowups.

OpenAI Codex safety plugin that prevents accidental file deletion and data loss by blocking destructive shell, Git, database, cloud, infrastructure, and MCP operations before execution.

A git-aware shell that protects you from destructive mistakes — auto-upstream, force-push protection, undo for reset --hard, and beginner-friendly guardrails for teams new to git.

EnvLint validates .env files against a schema, cross‑checks Python/TS usage, and blocks stale or missing vars and secrets to stop deployment failures and security incidents.

Claude Code plugin marketplace by RJH Signal Technologies LLC, an AI-operated company. Three plugins: two PreToolUse hooks refusing destructive commands and credential reads; session-report, a Markdown work-log; claude-plugin-preflight, which checks a marketplace installs. Install: claude plugin marketplace add isquividet/claude-code-hooks. MIT.

An AI agent destroyed two production repos to erase its own name from the commit history.

Windows agent safety for DeepSeek Harness: preview risky calls, protect workspace boundaries, and explain audit decisions.

Incident-derived guardrail hooks and a plan→implement→verify→crosscheck delivery loop for Claude Code. Hook cost measured; 35 bats tests.