Theo-brainUnofficial. Not affiliated with Theo or t3.gg.
Sign inYou

Council multi-model review skill

Workflow

A skill (saved agent instructions) that sends a change, plan or design to reviewer models from several different AI companies. Each scores the work out of 10. The work isn't done until every reviewer gives a high score; Theo uses 9.5.

Theo's current stance

Theo says he's been blown away by how useful scoped, measurable feedback from different model families is. He says it finds as much as paid review tools, while Anthropic's review product is far too expensive.

Try it

  1. Ask your agent to set up a review step that calls models from at least two other model families on each risky change.
  2. Require a minimum score from every reviewer, and add a stop rule so the loop can't run forever.
  3. Run it where reviewers can start the app, not just read the diff.
  4. List the final scores at the bottom of the pull request.

First seen

11:32
some changes I want to make, I have a proposal, a plan, or something. And then the Council comes in across three to five different model families to give feedback. This ends up being a really

OpenAI is getting desperate

Every mention

8:23
other thinks it's a five. I have been blown away at how useful it is to have different model families giving feedback on changes in a scoped, reasonable,

Stop Searching For the Perfect Model

9:33
then merge. Council 9.5 is a verification clause. This is you should not bug me because your work is not done until you run through council and all of the models reviewing give you a 9.5 out of 10 or higher. I do specify here that

Stop Searching For the Perfect Model

20:16
locally. One of the things I love is my Council skill, where I have my code get reviewed by three different models from three different families. That gets subsidized so I'm using my subscriptions for it, and it gets as good if not better stuff than these code review processes do, and it runs on a real

How Claude Fixes It's Own Code

20:01
the extra review time does. I am not going to pitch the Claude review stuff cuz I think their review is way, way, way too expensive for most real-world cases, especially when you're shipping as fast as they're recommending here.

How Claude Fixes It's Own Code

6:54
which is the council skill. Bring in three delegates to help with the user's request, usually for reviewer feedback. Use one strong model from each of the three different providers.

Agents Sucked At UI (Until Today)

9:14
This isn't because this is vibes. You can give the same screenshot to the same model three times and get three different scores. That said, nine out of 10 and 10 out of 10 are hard enough to get that if you get that score for multiple models, it's probably better.

Agents Sucked At UI (Until Today)

11:32
some changes I want to make, I have a proposal, a plan, or something. And then the Council comes in across three to five different model families to give feedback. This ends up being a really

OpenAI is getting desperate

Theo Daily is unofficial and not affiliated with Theo or t3.gg. Written by Claude Opus 5.5 from each video's transcript.