Council Multi-model review Asks three strong models from three different providers to review the work in parallel, scores each round out of 10 and repeats after fixes until all three are satisfied. @t3dotgg MIT

Skill · Multi-model review

Council

Asks three strong models from three different providers to review the work in parallel, scores each round out of 10 and repeats after fixes until all three are satisfied.

Author
Theo Browne (community)
Source
t3dotgg/tstack at version 11e37a7
Licence
MIT
Needs
Needs an account or credits: Access to models from three providers (paid); A harness that can run them as subagents, such as T3 Code
Works in
Terminal agents such as Claude Code, Codex and Cursor
Reviewed
Nov 2026, skill file read in full
Note
Every round runs three top-tier models, which costs accordingly. If it cannot reach three providers it reports that and does not substitute. Review scores are written into the pull request description.

Install only this skill

npx skills add t3dotgg/tstack@11e37a74d0a6868c121cd0910ab2b3bd9873b92a --skill council -g -y

Comes in these collections