Codex-only council review
Codex Council
One Codex pass gives you one train of thought. This runs several reviewers in parallel, makes them argue, scores the result, and hands back a decision worth defending.
- 6 reviewers
- Cost estimate first
- Browser evidence
- No outside APIs
The idea
Make Codex argue with itself, on purpose.
Each reviewer works from a fixed brief: architecture, reliability, security, product, red team, performance. Their answers are anonymized and ranked, a Chairman writes the verdict, and you see the token cost before anything runs. It's still one model wearing different hats, not rival labs. But the disagreement is real, and it catches what a single pass talks itself past.
How a run works
Four steps, every time.
Preflight
Before anything runs you get the mode, the agent count, and a token estimate. No surprise on the bill.
First opinions
Six named reviewers take the problem on independently, each guarding a different concern.
Review
Answers lose their authorship, get scored against a rubric, and are checked for gaps. Only the weak spots get a second round.
Synthesis
The Chairman writes the final call from what was actually saved. No invented test results, no made-up token counts.
The difference
A normal prompt answers. The council interrogates.
Fine when you just need one solid plan.
Review this proposal: add shareable session reports
with automatic redaction, HTML/JSON export,
and team handoff links.It gave a sensible local-export design and a couple of redaction tests. Useful, and roughly right.
Worth it when the plan has to survive privacy, reliability, and red-team scrutiny first.
Standard Council: review the same proposal.
Find blockers, dissent, verification gaps,
and the safest v1 scope.Same prompt, sharper outcome: it cut v1 down, killed the unsafe sharing claims, demanded fail-closed redaction, and added performance gates.