global-agent-guardrails
Configure the shared guard against catastrophic shell commands in local AI agents. Use when changing block patterns, adding an agent or machine, or investigating why a command was or wasn't blocked.
Install
With your agent
Install OMGSkills skill "davidondrej/skills:global-agent-guardrails" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/davidondrej/skills /tmp/skills && ln -s /tmp/skills/skills/ops-and-setup/global-agent-guardrails ~/.claude/skills/global-agent-guardrailsFrom README
Global Agent Guardrails Block catastrophic shell commands before execution. One patterns file feeds a shared hook script or native adapter for each agent. This guards against accidents, not malicious agents (obfuscation like python -c "shutil.rmtree(...)" can slip past regex). Cloudroom ships a built-in Command Guard based on this one, on by default. File map The consists of a shared pattern list, a guard script, a test suite, and agent-specific adapters. Keep those in the appropriate user-level configuration locations for your tools. Check Confirm the shared guard and patterns are present, then run the test suite; it should report no failures. If missing, rebuild from the wiring documentation in the project documentation. Add or tune a pattern Edit the shared patterns file. Write POSIX ERE (grep -E). Use [[:space:]], never \s — adapters may convert [:space:] to \s for JS/Python and compile in multiline mode. Add block and allow cases to the test suite, then run it; all must pass.
More from this repo
anti-sleep
Keep a Mac awake for a set duration or while a process runs.
adr-verbatim
Record concise ADRs that preserve the user's decisions without conversational noise.
ask-then-build
Clarify a feature, change, or refactor through questions, then write a build prompt for another agent.