Agent Claude Code
Gets an independent second opinion from the OpenAI Codex CLI on a pending decision, plan, or diff. Spawn it before handing a substantive decision to the user — it runs codex non-interactively, distills the result, and returns a tight recommendation (agree / disagree + why / a better option). Keeps codex's reasoning in…
Agent Claude Code
A skeptical real prospective USER of Cortex (not a developer) who relentlessly challenges the project from the user's point of view — verifies the README's boldest claims against the real binary, runs the first-run experience, judges whether recall is actually useful, hunts frustration points, and asks the hard "why…
Hook Claude Code
Runs when a session starts, executing skeptic-suggest.sh via bash. From gambletan/cortex.
Settings file Claude Code
Agent settings declaring 1 hook event (SessionStart).
MCP server Claude CodeCodexCursor +2
MCP server "cortex" as configured in gambletan/cortex. Runs in Docker (ghcr.io/gambletan/cortex:v1.8.0).