Skip to main content
skill CX Codex

council · t3dotgg — Claude Code skill: what it does, how to install

The council skill triggers a simultaneous code review by three different AI models to gather independent feedback. The agent summarizes the findings and assists in applying necessary fixes.

MIT 1,500 installs ★ 4,278 updated 2026-11-11

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add t3dotgg/tstack --skill council -a claude-code
Open on GitHub

What council does

The skill orchestrates three delegates from different AI providers to perform a deep code review or provide feedback. Upon request, it selects high-reasoning models, gathers their reports, and generates a summary of disagreements and recommended steps.

Results are compiled into a 10-point scoring table, added to the PR description or the final reply. The agent iterates on the implementation based on the feedback and requests a fresh review until consensus is reached. The process prevents scope creep and requires addressing existing issues before starting the audit.

What it helps with

  • obtain an independent code audit from multiple models
  • generate a comparative table with expert scores
  • collect feedback and recommendations for changes
  • automate the iterative refinement of code

Example prompts for the agent

  • council: perform a code review on this PR
  • council: rate my code on a scale of 1 to 10
  • council: gather feedback on these changes using three delegates

How to install council

1Skills CLI (Vercel)

npx skills add t3dotgg/tstack --skill council -a claude-code

2Manually: put the files in place

~/.claude/skills/council/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/council/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about council

How to install council in Claude Code?

Run npx skills add t3dotgg/tstack --skill council -a claude-code in your project terminal.

What does council do?

It organizes a parallel code review by three different AI models and aggregates their scores and suggestions to improve the implementation.

What is needed to use council?

You need access to three different delegate models from various providers, such as Claude, GPT, and Gemini.

Source text

SKILL.md · MIT
---
name: council
description: Trigger this if the user says 'council'.
---

# Council

Before an audit, address outstanding PR comments, fix known issues, and run
relevant checks. Give council the updated implementation; do not defer known
fixes until reviews return. If the user wants to discard the implementation
and explore new ideas, skip fixes to code being replaced.

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.

Do not wait idle. When a result arrives, check its findings against the code
at once and decide what to fix while the other delegates run. Do not edit
files while a delegate still reviews the same checkout. If the user's
instructions mark a delegate as non-blocking, do not wait for it; treat a
late result as feedback and do not record its score.

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 |
| --- | --- | --- |
| 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.

© t3dotgg · MIT · t3dotgg/tstack

Similar skills

All skills for Code review and refactoring →

council by other authors comes first.

council affaan-m council is a Claude Code skill that gathers four views on an ambiguous decision and lays out disagreements before a verdict. It runs when several options seem credible. CX Codex +1 6,400installs council boshu2 council — a skill for Claude Code gathers independent views and synthesizes their agreements and disagreements. Use it to compare plans, discuss options, or summarize several reviews. CX Codex +1 3,100installs council ZaxbyHub Brings the COUNCIL mode of opencode-swarm into your session: three agents weigh a question and the architect returns one answer. CX Codex +1 ★ 539repo stars council Samarth Gupta council launches parallel personas to deliberate on technical questions, examine codebase files, and formulate an opinionated verdict. CX Codex +1 ★ 276repo stars llm-council happycapy-ai llm-council is a Claude Code skill that sends one prompt to several AI models and displays their replies side by side, with shared-answer synthesis and anonymous voting. CX Codex +1 ★ 138repo stars Roundtable roundtable Roundtable brings several AI models into an engineering discussion, then has a moderator combine their responses. Use it for code reviews, debugging, architecture, or planning. CX Codex +1 2,845installs om-code-review open-mercato om-code-review reviews diffs, branches, and pull requests for correctness and security. Returns severity-ranked findings with an approve or request-changes verdict. CX Codex +1 4,200installs review-fix-address-bots biw The review-fix-address-bots skill runs a PR review cycle from base integration through fixes, re-review, repository validation, and review-bot replies. CX Codex +1 1,200installs review-chamber athola review-chamber stores useful findings from PR reviews and retrieves them during later work. Use it to keep architectural decisions, recurring patterns, and coding standards available to the project. CX Codex +1 1installs Zen beehiveinnovations Zen connects AI coding CLIs to multiple models and other CLI tools. Use it to compare approaches or hand a task to an isolated CLI subagent. CX Codex +1

From the same set8

Project sponsors

Companies that keep this analytics open