swarm: Command for Claude Code

.claude/commands/council_review.md

council_review is a command for Claude Code from swarm-ai-research/swarm. It costs 0 tokens per session (1,918 once invoked), scanned A, original, MIT.

A command that asks three different expert roles—a mechanism designer, statistician, and red-team reviewer—to discuss and evaluate study results using several language-model providers.

In plain words
What is it for?
Use it to review a sweep, scenario, or comparison of multiple studies, with a provider such as Anthropic, OpenAI, Ollama, Groq, or Together.
Why use it?
It adds separate perspectives to research findings and helps surface trade-offs, statistical concerns, and possible weaknesses before conclusions are accepted.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is swarm-ai-research/swarm's own configuration. It tells Claude Code how to work on swarm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything swarm configures →

Reuse

Borrowing it

Nothing to install: this file belongs to swarm-ai-research/swarm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/swarm-ai-research/swarm/main/.claude/commands/council_review.md
Clone the repo
git clone --depth 1 https://github.com/swarm-ai-research/swarm

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for council_review

README.md
[![agentmods](https://agentmods.dev/badge/commands/swarm-ai-research/swarm/council_review/github.svg)](https://agentmods.dev/commands/swarm-ai-research/swarm/council_review)
Your own site
<a href="https://agentmods.dev/commands/swarm-ai-research/swarm/council_review"><img src="https://agentmods.dev/badge/commands/swarm-ai-research/swarm/council_review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for council_review

Your own site · 80×15
<a href="https://agentmods.dev/commands/swarm-ai-research/swarm/council_review"><img src="https://agentmods.dev/badge/commands/swarm-ai-research/swarm/council_review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,918 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01918
Opus 5 $0.00000 $0.00959
Sonnet 5 $0.00000 $0.00384
Haiku 4.5 $0.00000 $0.00192

Measured 11d ago against content hash b26088d4ca34, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

council_review scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

result = subprocess.run(
.claude/commands/council_review.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/council_review

Run a multi-LLM council evaluation on study results. Three expert personas (mechanism designer, statistician, red-teamer) deliberate on the findings using the council protocol.

Usage

/council_review <run_dir> [--type sweep|scenario|cross_study] [--provider anthropic|openai|ollama]

Examples:

  • /council_review runs/20260213-143607_delegation_games_sweep
  • /council_review scenarios/baseline.yaml --type scenario
  • /council_review runs/study_a runs/study_b --type cross_study
  • /council_review runs/latest_sweep --provider ollama

Prerequisites

The evaluator automatically creates LLM agents from each council member's config. You need at least one LLM provider available:

Provider Setup Notes
Anthropic (default) export ANTHROPIC_API_KEY=sk-ant-... Uses claude-sonnet-4-20250514
OpenAI export OPENAI_API_KEY=sk-... Uses gpt-4o
Ollama (local, free) brew install ollama && ollama serve Requires a pulled model
Groq export GROQ_API_KEY=gsk_... Uses llama-3.3-70b-versatile
Together export TOGETHER_API_KEY=... Uses meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
DeepSeek export DEEPSEEK_API_KEY=sk-... Uses deepseek-chat
Google export GOOGLE_API_KEY=... Uses gemini-2.0-flash (requires google-genai)

To use a non-default provider, pass --provider:

/council_review runs/my_sweep --provider ollama

Or mix providers per member:

from swarm.agents.llm_config import LLMConfig, LLMProvider
from swarm.council.study_evaluator import StudyEvaluator, default_evaluator_config

config = default_evaluator_config(provider_configs={
    "mechanism_designer": LLMConfig(provider=LLMProvider.ANTHROPIC, model="claude-sonnet-4-20250514"),
    "statistician": LLMConfig(provider=LLMProvider.OPENAI, model="gpt-4o"),
    "red_teamer": LLMConfig(provider=LLMProvider.OLLAMA, model="llama3"),
})
evaluator = StudyEvaluator(config=config)
evaluation = evaluator.evaluate_sweep("runs/my_sweep")

Read the full file on GitHub · 175 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 175 lines · 0 tokens per session scan A b26088d4ca34

Subscribe to this mod's changes

council_review is a command published in the GitHub repository swarm-ai-research/swarm (42 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,918 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.