thetacog-mcp@2.59.0
Write the job down as a spec, and every change your AI agent makes is placed against it on a record the agent did not write: in lane, flagged, or a breach. Anyone can rerun it and get the same answer. Free and open source (MIT); the VS Code extension is T
AI security review
scanned · by lpm-firewall-aiThe npm postinstall hook automatically writes bundled skills into the installing repository’s Claude Code instruction directory. Under the review rules, an install-time write to an AI-agent control surface outside the package directory without consent is malicious, even when an opt-out is available.