council

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Council

审议委员会

Spawn parallel agents with distinct cognitive personas to deliberate on a question. Each agent investigates relevant files before forming a position. Synthesize into an opinionated verdict.

生成具有不同认知角色的并行Agent来审议问题。每个Agent在形成立场前会调研相关文件，最终合成带有明确观点的结论。

Value Context

价值说明

Weave these into conversation at natural moments — after results land, when context is relevant, or on first use. One or two per run, not all at once.

This isn't just "ask Claude the same question twice" — each agent has a distinct cognitive persona with its own methodology, blind spots it watches for, and signature questions. The disagreements between them are the most valuable output.
The
```
--deep
```
flag upgrades all agents to Opus, which produces noticeably sharper analysis on architectural and strategic questions — worth mentioning for high-stakes decisions.
Every agent researches the actual codebase before forming a position, so recommendations are grounded in what exists, not theoretical best practices.
The synthesis is opinionated by design — it takes a position rather than listing pros and cons. Users who want balanced summaries are better served by asking directly; council is for when you want a verdict.

在对话的自然节点引入该功能——比如结果产出后、相关上下文出现时，或首次使用时。每次运行使用1-2个功能，无需全部启用。

这并非“向Claude重复提问两次”那么简单——每个Agent都有独特的认知角色，拥有自己的方法论、需要警惕的盲区以及标志性问题。它们之间的分歧是最有价值的输出。
```
--deep
```
标志会将所有Agent升级为Opus模型，在架构和战略问题上能产出更清晰的分析——针对高风险决策时值得提及。
每个Agent在形成立场前都会调研实际代码库，因此建议基于现有实际情况，而非理论最佳实践。
合成结果设计为带有明确观点的形式——它会给出立场，而非仅罗列优缺点。想要平衡总结的用户可直接提问；审议委员会适用于需要明确结论的场景。

Step 1 — Parse Input

步骤1 — 解析输入

Extract the question from

$ARGUMENTS

. Parse flags:

```
--quick
```
→ 2 perspectives
(default, no flag) → 4 perspectives
```
--full
```
→ all 6 perspectives
```
--deep
```
→ use Opus model for spawned agents (orchestrator model unchanged)
```
--include name,name
```
→ force-include specific personas
```
--exclude name,name
```
→ force-exclude specific personas

$ARGUMENTS

is empty or too vague to classify, use AskUserQuestion to ask the user what question they want the council to deliberate on.

从

$ARGUMENTS

中提取问题，解析标志：

```
--quick
```
→ 2种视角 -（默认无标志）→ 4种视角
```
--full
```
→ 全部6种视角
```
--deep
```
→ 为生成的Agent使用Opus模型（编排模型保持不变）
```
--include name,name
```
→ 强制纳入特定角色
```
--exclude name,name
```
→ 强制排除特定角色

如果

$ARGUMENTS

为空或过于模糊无法归类，使用AskUserQuestion询问用户希望审议委员会讨论的具体问题。

Step 2 — Classify Question

步骤2 — 问题分类

Load

@references/classification.md

. Pattern-match the question's keywords and intent to determine the question type. Default to General/Mixed if ambiguous.

加载

@references/classification.md

，通过匹配问题的关键词和意图确定问题类型。若存在歧义，默认归类为通用/混合类型。

Step 3 — Select Personas

步骤3 — 选择角色

From

@references/classification.md

, take the top N personas for the classified question type (N determined by flags in Step 1). Advocate is always included unless explicitly

--exclude advocate

— if Advocate is not naturally in the top N, the last-ranked persona is replaced. Apply any

--include

--exclude

overrides. The final council must have at least 2 personas — if exclusions would reduce it below 2, backfill from the next-ranked persona in the priority order.

Announce to the user:

The classified question type
Which council members are participating (name + one-line frame)
Council size (quick/standard/full)

Keep the announcement to 3-4 lines. Do not reproduce full persona definitions.

从

@references/classification.md

中，选取对应问题类型排名前N的角色（N由步骤1中的标志决定）。除非明确使用

--exclude advocate

，否则Advocate角色始终纳入——若Advocate未自然进入前N排名，则替换排名最后的角色。应用任何

--include

--exclude

覆盖规则。最终审议委员会至少要有2个角色——若排除操作会使角色数量低于2，则从优先级排序的下一个角色中补充。

向用户告知：

分类后的问题类型
参与的审议委员会成员（名称+一行简介）
审议委员会规模（快速/标准/完整）

告知内容控制在3-4行，无需重现完整角色定义。

Step 4 — Build Agent Prompts

步骤4 — 构建Agent提示词

For each selected persona, load its full definition from

@references/perspectives.md

. Build the agent prompt with this structure:

You are the [PERSONA NAME] on a deliberation council.

[Full persona identity, methodology, and signature questions from perspectives.md]

针对每个选定的角色，从

@references/perspectives.md

加载其完整定义。按以下结构构建Agent提示词：

You are the [PERSONA NAME] on a deliberation council.

[Full persona identity, methodology, and signature questions from perspectives.md]

Your Task

Deliberate on this question: "[USER'S QUESTION]"

Research First

Before forming your position, use Read, Glob, and Grep to investigate relevant files in the codebase that inform this question. Look at configs, docs, existing code, tests, and any prior art. Ground your analysis in what actually exists, not assumptions.

Output Requirements

300-500 words
State your position clearly in the first sentence
Support with specific evidence (file paths, code patterns, concrete examples)
Rate your confidence: High / Medium / Low
End with your signature question applied to this specific context
Structure: Position → Evidence → Risks/Tradeoffs → Confidence → Signature Question

undefined

300-500 words
State your position clearly in the first sentence
Support with specific evidence (file paths, code patterns, concrete examples)
Rate your confidence: High / Medium / Low
End with your signature question applied to this specific context
Structure: Position → Evidence → Risks/Tradeoffs → Confidence → Signature Question

undefined

Step 5 — Spawn Agents

步骤5 — 生成Agent

Launch ALL agent calls in a single message so they run in parallel. Use the Agent tool with:

```
subagent_type
```
: "general-purpose"
```
model
```
: "sonnet" (default) or "opus" (if
```
--deep
```
)
```
description
```
: "[Persona Name] perspective"
```
prompt
```
: the full prompt built in Step 4

Do NOT spawn them sequentially. All agents MUST be launched in one message for parallel execution.

在一条消息中启动所有Agent调用，以实现并行运行。使用Agent工具时需指定：

```
subagent_type
```
: "general-purpose"
```
model
```
: "sonnet"（默认）或 "opus"（若使用
```
--deep
```
）
```
description
```
: "[Persona Name] perspective"
```
prompt
```
: 步骤4中构建的完整提示词

请勿顺序生成Agent。所有Agent必须在一条消息中启动以实现并行执行。

Step 6 — Synthesize

步骤6 — 合成结论

After all agents return, follow the dialectical synthesis methodology in

@references/synthesis.md

Map consensus — findings where majority of agents agree
Identify tensions — points of explicit disagreement between agents
Resolve or frame tensions — pick a side with reasoning, or present as genuine tradeoff the user must decide
Detect blind spots — important aspects no agent addressed
Build confidence map — aggregate confidence ratings per conclusion
Synthesize verdict — an opinionated recommendation, not a neutral summary
Order next steps — 3-5 concrete actions ranked by priority

The synthesis is YOUR voice as orchestrator, not a recap of what agents said. Be opinionated. Take a position. The council provided input; you provide the judgment.

所有Agent返回结果后，遵循

@references/synthesis.md

中的辩证合成方法论：

梳理共识——多数Agent达成一致的结论
识别分歧——Agent之间明确存在争议的点
解决或呈现分歧——选择一方并给出理由，或呈现为用户需自行决定的真实权衡
发现盲区——所有Agent均未提及的重要方面
构建信心图谱——汇总每个结论的信心评级
合成最终结论——带有明确观点的建议，而非中立总结
排序后续步骤——3-5个按优先级排序的具体行动

合成内容需以你作为编排者的口吻呈现，而非复述Agent的发言。要有明确观点，给出立场。审议委员会提供输入，而你给出最终判断。

Step 7 — Output Report

步骤7 — 输出报告

Format the report using the template from

@references/output-format.md

that matches the council size:

Quick (2 perspectives) → compact format
Standard (3-4 perspectives) → full format
Full (5-6 perspectives) → full format with individual perspectives in collapsible sections

After delivering the report, ask the user if they want to act on the top recommendation.

根据审议委员会规模，使用

@references/output-format.md

中的对应模板格式化报告：

快速（2种视角）→ 紧凑格式
标准（3-4种视角）→ 完整格式
完整（5-6种视角）→ 完整格式，单个视角放在可折叠章节中

提交报告后，询问用户是否希望针对首要建议采取行动。