council
Review with different models
Bring different models together to challenge a change and compare notes.
Ask your agent
councilStart a new session after installing, then use this command in your project.
How it works
- Choose reviewers
- independent reviews
- compare findings
- resolve
Needs access to models from different providers. Available reviewers depend on your harness.
Install council
Pick your harness and how you want to install. Copy the commands, then ask for a skill by name.
Claude Code / all projects
npx skills add 0libote/ostack --agent claude-code --global --skill councilUses the skills CLI. Requires Node.js and npm; installs the skills listed in the command.
Available across your projects. Start a new agent session after installing.
Read the skill instructions
The full SKILL.md, as shipped in this collection. Supporting files are in the source repository.
---
name: council
description: Trigger this if the user says 'council'.
---
# Council
Bring in three delegates to help with the user's request, usually for review
or feedback. Use one strong model from each of three different providers, at
high reasoning effort. If the user's instructions name council members, use
those. Otherwise pick the latest flagship model from each provider.
In T3 Code, use `orchestrator_capabilities` to resolve the models, then
`delegate_task` to start one delegate per model in parallel. Elsewhere, use
the harness's subagent tools. If you cannot reach three providers, or a named
member is unavailable, report it instead of substituting.
Give each delegate the request and relevant context. For review or feedback,
keep their work read-only. Collect their responses and summarize the useful
findings, disagreements, and recommended next steps.
For a code review, ask each delegate for a score out of 10.
Count each full review pass as one round.
A fresh review after fixes starts a new round.
If the work ends in a pull request, put the results in the PR description.
Put this section before the model and harness line at the end:
```markdown
## Council review
Rounds: 2
| Delegate | Round 1 | Round 2 |
| --- | --- | --- |
| Delegate A | 7/10 | 9/10 |
| Delegate B | 8/10 | 10/10 |
| Delegate C | 7/10 | 9/10 |
```
If a delegate gives no score, write `no score`. Do not invent one.
If the PR is open, edit the description. Do not post a comment for this.
If there is no PR, put the same results in the final reply only.
If you agree with their recommendations, make the changes and request a fresh
review after. Continue this process until all delegates are satisfied with the
outcome.
Do not let repeated reviews result in scope creep. It is your job to fight to
keep scope limited.