thetacog-mcp@2.59.1
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 package’s automatic postinstall writes bundled agent skills into the installing project’s .claude/skills directory without requiring a user request. This meets the install-time AI-agent control-surface hijack rule; the opt-out does not change the default behavior.