conciliumlisted

Adversarial cross-model review for hard, load-bearing tasks — combining frontier models: the Claude session (Opus 5 or Fable 5 as the intended orchestrator) hands a claim, diff, or result to an OpenAI model (gpt-5.6-sol / gpt-5.6-terra / gpt-5.5, via the codex CLI on ChatGPT-subscription auth, no API key), which probes it with falsification attempts and PROPOSES a verdict; the orchestrator checks the probe and RATIFIES. Use whenever the user wants a second opinion from a different model, a cross-model or concilium review, adversarial verification of a research claim, benchmark number, or diff, says "have GPT/codex check this", wants codex set up as a reviewer, needs to switch codex models mid-session (park-and-resume), is tiering work across codex models, or wants to LOOP/iterate review rounds until a disputed claim converges.
raichominev/concilium · ★ 2 · AI & Automation · score 75

Install: claude install-skill raichominev/concilium

# Concilium — cross-model adversarial review A second, *different* model reviews your (or the user's) claims adversarially. Different model lineage means different blind spots — that's the value. The reviewer PROPOSES; the calling session RATIFIES. Never let either side's confidence substitute for evidence. Designed to be orchestrated from Claude Code — **Opus 5 and Fable 5 are both first-class ratification seats** (measured at chair parity on a blind outcome-prediction benchmark; any Claude model can drive the loop, but the ratifier should be one of the two). The GPT side (sol/terra/5.5 via codex) does the independent probing and mechanical execution — and that cross-family seat is load-bearing: it measurably catches what same-family chairs jointly miss. ## Prerequisites (check once per environment) 1. `codex login status` → must say "Logged in using ChatGPT" (subscription OAuth — an API key is NOT needed and a subscription can NOT be used as one; don't attempt proxy/router bridges). 2. Discover available models: `codex debug models` or `~/.codex/models_cache.json`. If a model errors "requires a newer version of Codex", run `codex update` and retry. 3. First time in a new environment, run the calibration bootstrap (references/setup.md) before trusting verdicts: a known-truth reasoning test, then one simple real task, then (optionally) a head-to-head to pick tier models. ## Tier matrix (defaults are current-day models — override per installation) | Tier | De