A proof-of-concept destructive-command guard for coding agents.

Guard Pi shell commands with Destructive Command Guard.

Agent harness kit for Claude Code — installs verification sensors, destructive-command guards, checkpoint recovery, observability logs, and ratchet skills into your project

Structured, safe Git tool family for DeepSeek Harness: status/diff/log/branch/stage/commit/stash/show/fetch/pull/remote/checkout with a destructive-command guard.

Zero-latency AI terminal guardian and destructive command interceptor powered by Jev System 1 model

LLM security guardrails for Claude Code — jailbreak detection, prompt-injection and web-content scanning, data-exfiltration blocking, and destructive-command authorization. Enforced by hooks on every prompt, shell command, fetched page and file write.

LLM security guardrails for OpenCode — jailbreak detection, prompt-injection and web-content scanning, and destructive-command authorization. Bundles enforcing hooks plus the AgentGuards MCP server.

Agent security framework. Immutable audit trail, permission policies, self-modification detection, destructive command guard.

SSH MCP server for AI agents — remote commands, file transfer, log search and server audits through OpenSSH, with destructive-command checks. Works with Claude Code, Codex, Gemini CLI and any MCP client.

Deterministic destructive-command guard + inviolable-constraint policy engine and deviation state machine for the Pi coding agent

Security plugin for OpenClaw - secret detection, PII filtering, and destructive command protection

Run Linux commands from Windows through WSL, essentially matching a native Linux DSH for command execution: background jobs, stdin, path translation, a destructive-command guard and a WSL capability report. WSL calls run below the DSH sandbox, and a proje

Fail-closed destructive-command approval gate and safe-operations skill for the Pi coding agent.

Checksum algorithms and flexible checksums middleware for the AWS SDK

Simple extension to integrate oh-my-pi with [destructive command guard](https://github.com/Dicklesworthstone/destructive_command_guard)

Guardrail environment for AI-assisted work with Claude Code: rules, skills, agents and a destructive-command guard hook that keep the agent in scope, save tokens and gate every commit. Curated by a West African dev.

Recursively walk and transform EcmaScript AST

Bridge between dcg (Destructive Command Guard) and Hermes Agent — pre-command scanning, cron-safe reports, workspace protection for AI agent workflows

A Modern JavaScript Date Library

WrongStack Kanban as a project-scoped MCP server with read-only, writable, destructive, and live-watch capability tiers.