brains-trust

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Brains Trust

Consult other leading AI models for a second opinion. Not limited to code — works for architecture, strategy, prompting, debugging, writing, or any question where a fresh perspective helps.

咨询其他顶尖AI模型以获取第二意见。不仅限于代码——适用于架构、策略、提示词、调试、写作或任何需要全新视角的问题。

Setup

设置

Set at least one API key as an environment variable:

bash

undefined

设置至少一个API密钥作为环境变量：

bash

undefined

Recommended — one key covers all providers

export OPENROUTER_API_KEY="your-key"

Optional — direct access (often faster/cheaper)

export GEMINI_API_KEY="your-key" export OPENAI_API_KEY="your-key"


OpenRouter is the universal path — one key gives access to Gemini, GPT, Qwen, DeepSeek, Llama, Mistral, and more.

export GEMINI_API_KEY="your-key" export OPENAI_API_KEY="your-key"


OpenRouter是通用方案——一个密钥即可访问Gemini、GPT、Qwen、DeepSeek、Llama、Mistral等更多模型。

Current Models

当前模型

Do not use hardcoded model IDs. Before every consultation, fetch the current leading models:

https://models.flared.au/llms.txt

This is a live-updated, curated list of ~40 leading models from 11 providers, filtered from OpenRouter's full catalogue. Use it to pick the right model for the task.

For programmatic use in the generated Python script:

https://models.flared.au/json

请勿使用硬编码的模型ID。每次咨询前，获取当前的顶尖模型列表：

https://models.flared.au/llms.txt

这是一个实时更新的精选列表，包含来自11个提供商的约40款顶尖模型，从OpenRouter的完整目录中筛选而来。使用它为任务选择合适的模型。

若要在生成的Python脚本中程序化使用，请访问：

https://models.flared.au/json

Consultation Patterns

咨询模式

Pattern	When	What happens
Single (default)	Quick second opinion	Ask one model, synthesise with your own view
Consensus	Important decision, want confidence	Ask 2-3 diverse models in parallel, compare where they agree/disagree
Devil's advocate	Challenge an assumption	Ask a model to explicitly argue against your current position

For consensus, pick models from different providers (e.g. one Google, one OpenAI, one Qwen) for maximum diversity of perspective.

模式	适用场景	执行逻辑
单一意见（默认）	快速获取第二意见	调用一个模型，结合你自己的观点进行综合
多模型共识	重要决策，希望获得信心	并行调用2-3个不同的模型，对比它们的异同点
魔鬼代言人	挑战现有假设	要求模型明确反驳你当前的立场

对于共识模式，请选择来自不同提供商的模型（例如一个Google、一个OpenAI、一个Qwen）以获取最大的视角多样性。

Modes

功能模式

Mode	When	Model tier
Code Review	Review files for bugs, patterns, security	Flash
Architecture	Design decisions, trade-offs	Pro
Debug	Stuck after 2+ failed attempts	Flash
Security	Vulnerability scan	Pro
Strategy	Business, product, approach decisions	Pro
Prompting	Improve prompts, system prompts, KB files	Flash
General	Any question, brainstorm, challenge	Flash

Pro tier: The most capable model from the chosen provider (e.g.

google/gemini-3.1-pro-preview

openai/gpt-5.4

). Flash tier: Fast, cheaper models for straightforward analysis (e.g.

google/gemini-3-flash-preview

qwen/qwen3.5-flash-02-23

模式	适用场景	模型层级
代码评审	检查文件中的漏洞、模式问题和安全隐患	Flash
架构设计	设计决策、权衡取舍	Pro
调试	尝试2次以上仍未解决问题时	Flash
安全检测	漏洞扫描	Pro
策略制定	业务、产品、方法决策	Pro
提示词优化	改进提示词、系统提示词、知识库文件	Flash
通用咨询	任何问题、头脑风暴、挑战假设	Flash

Pro层级：所选提供商中能力最强的模型（例如

google/gemini-3.1-pro-preview

、

openai/gpt-5.4

）。 Flash层级：用于简单分析的快速、低成本模型（例如

google/gemini-3-flash-preview

、

qwen/qwen3.5-flash-02-23

）。

Workflow

工作流程

Detect available keys — check
```
OPENROUTER_API_KEY
```
,
```
GEMINI_API_KEY
```
,
```
OPENAI_API_KEY
```
in environment. If none found, show setup instructions and stop.
Fetch current models —
```
WebFetch https://models.flared.au/llms.txt
```
and pick appropriate models based on mode (pro vs flash) and consultation pattern (single vs consensus). If user requested a specific provider ("ask gemini"), use that.
Read target files into context (if code-related). For non-code questions (strategy, prompting, general), skip file reading.
Build prompt using the AI-to-AI template from references/prompt-templates.md. Include file contents inline with
```
--- filename ---
```
separators. Do not set output token limits — let models reason fully.
Write prompt to file at
```
.claude/artifacts/brains-trust-prompt.txt
```
— never pass code inline via bash arguments (shell escaping breaks it).
Generate and run Python script at
```
.claude/scripts/brains-trust.py
```
using patterns from references/provider-api-patterns.md:
- Reads prompt from
```
.claude/artifacts/brains-trust-prompt.txt
```
- Calls the selected API(s)
- For consensus mode: calls multiple APIs in parallel using
```
concurrent.futures
```
- Saves each response to
```
.claude/artifacts/brains-trust-{model}.md
```
- Prints results to stdout
Synthesise — read the responses, present findings to the user. Note where models agree and disagree. Add your own perspective (agree/disagree with reasoning). Let the user decide what to act on.

检测可用密钥 —— 检查环境变量中的
```
OPENROUTER_API_KEY
```
、
```
GEMINI_API_KEY
```
、
```
OPENAI_API_KEY
```
。如果未找到任何密钥，显示设置说明并停止。
获取当前模型 —— 通过
```
WebFetch https://models.flared.au/llms.txt
```
获取，并根据功能模式（Pro vs Flash）和咨询模式（单一意见 vs 多模型共识）选择合适的模型。如果用户指定了特定提供商（例如"ask gemini"），则使用该提供商的模型。
读取目标文件到上下文（如果与代码相关）。对于非代码问题（策略、提示词、通用咨询），跳过文件读取。
构建提示词 —— 使用references/prompt-templates.md中的AI-to-AI模板。将文件内容用
```
--- filename ---
```
分隔符内联到提示词中。请勿设置输出令牌限制 —— 让模型充分推理。
将提示词写入文件 —— 保存到
```
.claude/artifacts/brains-trust-prompt.txt
```
，切勿通过bash参数内联传递代码（会导致shell转义错误）。
生成并运行Python脚本 —— 保存到
```
.claude/scripts/brains-trust.py
```
，使用references/provider-api-patterns.md中的模式：
- 从
```
.claude/artifacts/brains-trust-prompt.txt
```
  读取提示词
- 调用选定的API(s)
- 对于共识模式：使用
```
concurrent.futures
```
  并行调用多个API
- 将每个响应保存到
```
.claude/artifacts/brains-trust-{model}.md
```
- 将结果打印到标准输出
综合分析 —— 读取响应，向用户呈现结果。标注模型的异同点。添加你自己的观点（同意/不同意并说明理由）。让用户决定后续行动。

When to Use

使用场景

Good use cases:

Before committing major architectural changes
When stuck debugging after multiple attempts
Architecture decisions with multiple valid options
Reviewing security-sensitive code
Challenging your own assumptions on strategy or approach
Improving system prompts or KB files
Any time you want a fresh perspective

Avoid using for:

Simple syntax checks (Claude handles these)
Every single edit (too slow, costs money)
Questions with obvious, well-known answers

适用场景：

提交重大架构变更前
多次尝试仍无法调试解决问题时
存在多个有效选项的架构决策
评审安全敏感代码
挑战自己在策略或方法上的假设
改进系统提示词或知识库文件
任何需要全新视角的时刻

不适用场景：

简单语法检查（Claude可处理此类任务）
每一次微小编辑（速度太慢，成本较高）
答案明显且广为人知的问题

Critical Rules

关键规则

Never hardcode model IDs — always fetch from
```
models.flared.au
```
first
Never cap output tokens — don't set
```
max_tokens
```
or
```
maxOutputTokens
```
Always write prompts to file — never pass via bash arguments
Include file contents inline — attach code context directly in the prompt
Use AI-to-AI framing — the model is advising Claude, not talking to the human

请勿硬编码模型ID —— 始终先从
```
models.flared.au
```
获取
请勿限制输出令牌 —— 不要设置
```
max_tokens
```
或
```
maxOutputTokens
```
始终将提示词写入文件 —— 切勿通过bash参数传递
内联包含文件内容 —— 将代码上下文直接嵌入提示词中
使用AI-to-AI框架 —— 模型是为Claude提供建议，而非直接与人类对话

Reference Files

参考文件

When	Read
Building prompts for any mode	references/prompt-templates.md
Generating the Python API call script	references/provider-api-patterns.md

场景	参考文件
构建任何模式的提示词时	references/prompt-templates.md
生成Python API调用脚本时	references/provider-api-patterns.md