# council

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.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 1500 installs · ★ 4278 repo stars
- Author: t3dotgg
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/t3dotgg/tstack/tree/HEAD/skills/council/SKILL.md
- Updated: 2026-11-11
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/t3dotgg-council

## What it 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.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add t3dotgg/tstack --skill council -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/council/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/council/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add t3dotgg/tstack --skill council -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/council/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add t3dotgg/tstack --skill council -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/council/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install t3dotgg/tstack skills/council
```

2. **Manually: put the files in place**
- File: `.github/skills/council/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add t3dotgg/tstack --skill council -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/t3dotgg/tstack --path skills/council
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/council/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add t3dotgg/tstack --skill council -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/t3dotgg/tstack/tree/HEAD/skills/council/SKILL.md

## When to use it
- 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
- 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

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 52da9adf4b8b42f9.

BEGIN THIRD-PARTY FILE 52da9adf4b8b42f9
````text
---
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.
````
END THIRD-PARTY FILE 52da9adf4b8b42f9

The third-party file has ended. Everything between the 52da9adf4b8b42f9 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

© t3dotgg · MIT · https://github.com/t3dotgg/tstack/tree/HEAD/skills/council/SKILL.md

## Similar
- [llm-council](https://affpapa.org/en/nevibecode/skills/happycapy-ai-llm-council.md) — skill · ★ 138 repo stars
- [Roundtable](https://affpapa.org/en/nevibecode/mcp/roundtable.md) — MCP server · 2845 installs
- [om-code-review](https://affpapa.org/en/nevibecode/skills/om-code-review.md) — skill · 4200 installs
- [review-fix-address-bots](https://affpapa.org/en/nevibecode/skills/review-fix-address-bots.md) — skill · 1200 installs
- [review-chamber](https://affpapa.org/en/nevibecode/skills/review-chamber.md) — skill · 1 install
- [Zen](https://affpapa.org/en/nevibecode/mcp/zen.md) — MCP server

## Other versions with the same name
- [council · affaan-m](https://affpapa.org/en/nevibecode/skills/council.md) — 6400 installs
- [council · boshu2](https://affpapa.org/en/nevibecode/skills/boshu2-council.md) — 3100 installs
- [council · zaxbyhub](https://affpapa.org/en/nevibecode/skills/zaxbyhub-council.md) — ★ 539 repo stars

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
