Skip to content
Skills Library
AI & agents · Analysis

consensus

/consensus

多视角共识决策 - 使用 Codex 主线与只读 child agent 获取架构、实现和风险视角并综合决策。

Repository
oh-my-codex ↗
Licence
MIT
Last repository change
22.08.2026

Assessment and security

96/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability21 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
3
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 22.08.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

多视角共识决策 - 使用 Codex 主线与只读 child agent 获取架构、实现和风险视角并综合决策。

Original author description

多视角共识决策 - 使用 Codex 主线与只读 child agent 获取架构、实现和风险视角并综合决策。

How it works

  1. 核心功能
  2. 触发场景
  3. Workflow
  4. 输出格式
  5. Guardrails
Original SKILL.md headings · 102 lines, 171 words
SKILL.md preview
---
name: consensus
description: 多视角共识决策 - 使用 Codex 主线与只读 child agent 获取架构、实现和风险视角并综合决策。
auto_invoke: true
tags: [consensus, decision, codex-native, multi-agent]
version: 0.2.0
source: fork
checksum: 8f5a3a75601e12c985ba02ce5a487e6b8afa846cd47eb1e2667cdec962bc3e5a
updated_at: 2026-05-29T11:50:00+08:00
layer: research
---

# Consensus - Codex 原生多视角共识

## 核心功能

针对技术选型、架构决策、方案取舍和高风险变更,使用 Codex 主线协调多个只读 child agent 形成共识。不调用外部模型 CLI。

## 触发场景

- "多方意见"
- "技术决策需要共识"
- "consensus 分析"
- "三方协作决策"
- "帮我比较这些方案"

手动触发:

```text
使用 consensus 分析:<决策问题>
```

## Workflow

### Step 1: 明确决策问题

收集:

- 决策问题
- 候选方案
- 约束条件
- 成功标准
- 不可接受风险
- 决策截止时间

### Step 2: 派发独立视角

推荐三个视角:

```text
spawn_agent(agent_type="explorer", message="<architecture/context perspective>")
spawn_agent(agent_type="reviewer", message="<risk/correctness perspective>")
spawn_agent(agent_type="docs-researcher", message="<docs/facts verification perspective>")
wait_agent
close_agent
```

如 agent 不可用,在当前回复内用 `[ARCHITECTURE]`、`[REVIEW]`、`[FACTS]` 三块自演。

### Step 3: 各视角输出要求

每个视角必须输出:

- 明确立场:支持 / 反对 / 有条件支持
- 关键理由
- 最大风险
- 需要验证的假设
- 推荐的最小下一步

### Step 4: 主线综合

Codex 主线对比观点:

- 一致点
- 分歧点
- 分歧是否由事实差异、价值权重或风险偏好造成
- 最终建议
- 置信度
- 验证计划

## 输出格式

```markdown
## Consensus Decision

### Decision
[决策问题]

### Perspectives
| Perspective | Position | Key Reasons | Risks | Confidence |

### Agreements
- [共同结论]

### Disagreements
- [分歧 + 原因]

### Recommendation
[最终建议]

### Verification Plan
1. [step] -> verify: [check]

### When To Revisit
[触发重新决策的条件]
```

## Guardrails

- 不把"多个角色都同意"当作证据;必须列出事实来源。
- 对不可验证假设标记低置信度。
- 对高风险决策给阶段性试点或回滚方案。
Files in this package (3)
  • HOW_TO_USE.md 1 KB
  • README.md 1 KB
  • SKILL.md 2 KB

Versions

RepositoryScoreLicence
This page · materialofair/oh-my-codex96MIT
corespeed-io/consensus100MIT
cofin/flow100Apache-2.0

Database snapshot: 13.11.2026 · package version 19a02c1952b6 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 96multi-model-research
    多代理技术调研 - 使用 Codex 主线与只读 child agent 并行收集架构、实现、文档和风险视角。
  • 100dev-ccg
    Tri-model orchestration — run the same task through Claude + Codex + Gemini in parallel and synthesize the best answer. Use for high-stakes decisions where multi-model consensus reduces single-model bias.
  • 92ase-meta-quorum
    Query multiple foreign AIs in parallel and synthesize a consensus ("quorum") answer with a consensus rating. Use when the user wants a quorum, a consensus answer, or the opinions of multiple AIs on a question.
  • 90swarm-consensus
    Implement voting mechanisms (majority, weighted) to resolve inter-agent conflicts. Use when: swarm consensus.
  • 9803
    Run an autonomous consensus round between agent peers on several machines: they negotiate a decision over a shared channel and execute it without a human relaying messages. Use when multiple machines must agree on a change. Triggers: "/03", "work it out among yourselves", "find…
  • 100hive-mind-advanced
    Queen-led collective-intelligence coordination with consensus mechanisms and persistent shared memory. Use when orchestrating a large swarm of agents under a lead coordinator, building consensus across agents, or maintaining durable cross-agent memory.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.