Get parallel feedback on a request from three delegates using models from different providers. The skill gathers their findings, summarizes agreements and disagreements, and suggests next steps; code reviews also include a score from each delegate.
Trigger this if the user says 'council'.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
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, for example Claude Opus, GPT Sol, and Gemini Pro.
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:
## Council review
Rounds: 2
| Delegate | Round 1 | Round 2 |
| --- | --- | --- |
| Claude Opus | 7/10 | 9/10 |
| GPT Sol | 8/10 | 10/10 |
| Gemini Pro | 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.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Monitor a pull request through reviews and CI checks, then respond to real failures and feedback. The skill helps determine when the latest changes meet the repository’s merge conditions; it reports readiness without merging unless the user asked for a merge.
Prepare and open a concise pull request by checking for an existing PR, reviewing the branch diff, and writing a clear title and problem-focused description. The skill also checks the submission text and attachments for secrets or private details.
Carry a requested code change from implementation through direct proof, review, pull request updates, and merge when the required checks pass. The workflow also tracks review findings and asks the user only when progress is blocked or a decision is outside its permission.
Take a requested change through implementation, proof, review, and pull request readiness, then hand it back without merging. It follows the full-send workflow for testing and review, checks the live pull request state, and reports whether it is ready, awaiting approval, or blocked.
Format comments posted on GitHub on the user’s behalf with clear attribution, then review the full Markdown for private details before posting. The skill covers PR comments, inline reviews, replies, and explanations for resolving feedback.
Review an older pull request against the current codebase, decide whether its goal still fits, and recommend modernization, rework, or closure. For useful changes, rebase the branch onto its latest base and report conflicts, checks, and results.