thetacog-mcp@2.56.0
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 postinstall hook automatically installs package-owned agent instructions into the consumer project, a first-party agent extension lifecycle risk. The inspected writer limits its scope and the steer skill gates actions behind --go, so the source supports a warning rather than a confirmed attack.