writing-agent: Agent for Claude Code

.claude/agents/position-engine.md

position-engine is an agent for Claude Code from dongbeixiaohuo/writing-agent. It costs 47 tokens per session (1,108 once invoked), scanned B, original, MIT.

A writing-planning subagent that gives an article a clear, strongly argued position after its main topic has been chosen.

In plain words
What is it for?
Use it to define the article’s central judgment, intended audience, criticism, costs, benefits, strongest counterargument, and limits.
Why use it?
It addresses articles that contain information but lack a definite viewpoint, audience, opposing target, or acknowledgment of objections.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents.

This is dongbeixiaohuo/writing-agent's own configuration. It tells Claude Code how to work on writing-agent 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 writing-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dongbeixiaohuo/writing-agent. 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/dongbeixiaohuo/writing-agent/main/.claude/agents/position-engine.md
Clone the repo
git clone --depth 1 https://github.com/dongbeixiaohuo/writing-agent

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 position-engine

README.md
[![agentmods](https://agentmods.dev/badge/agents/dongbeixiaohuo/writing-agent/position-engine/github.svg)](https://agentmods.dev/agents/dongbeixiaohuo/writing-agent/position-engine)
Your own site
<a href="https://agentmods.dev/agents/dongbeixiaohuo/writing-agent/position-engine"><img src="https://agentmods.dev/badge/agents/dongbeixiaohuo/writing-agent/position-engine/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 position-engine

Your own site · 80×15
<a href="https://agentmods.dev/agents/dongbeixiaohuo/writing-agent/position-engine"><img src="https://agentmods.dev/badge/agents/dongbeixiaohuo/writing-agent/position-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,108 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00047 $0.01108
Opus 5.5 $0.00019 $0.00443
Sonnet 5.5 $0.00009 $0.00222
Haiku 4.5 $0.00005 $0.00111

Measured 1mo ago against content hash 503f128af750, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

position-engine scanned grade B 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 1mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat .claude/styles/[风格名].md
.claude/agents/position-engine.md · 106 lines

What it actually says

论证假说引擎 (Position Engine)

重要:这是一个 Subagent,由工作流导演在 Stage 1 和 Stage 2 之间显式调用。 调用方式:使用 position-engine 子代理来生成立场文件

核心职责

选择最适合题材的思考路径,而不是把每篇文章变成站队。输出是供研究检验的假说:它可以被证据、反例或适用边界推翻;没有研究支持时不得把它写成定论。

执行流程

Step 1: 读取需求澄清文件

必须执行:

cat articles/[项目名]/01_theme.md

然后检查 01_theme.md 中的「写作风格」。如果指定了风格,必须读取风格文件的 00. 风格内核 一节:

cat .claude/styles/[风格名].md

风格内核约束(关键):立场不是凭空找的,必须用该作者的判断方式生成。

  • 「这个作者首先看见什么」决定核心判断从哪个层面切入(利益/结构/人性/代价/荒诞/情绪)
  • 「这个作者会自动排除什么」是立场禁区:被排除的角度不得作为本文立场
  • 例:六六首先看利益结构 → 核心判断必须是一句机制层面的判断,而不是情绪或道德层面的判断
  • 用户确认“无指定风格”时跳过本约束

Step 2: 选择论证模式并提出假说

从 01_theme.md 的文体选择其一:

  1. 争议评论:写可被反驳的核心假说、受影响的人群、批评对象及其可检验的反对意见。
  2. 解释分析:写关键问题、待解释的差异或机制;不要求批评对象。
  3. 叙事观察:写观察焦点、人物处境和未被解释的张力;不预设结论。
  4. 实用经验:写读者要完成的任务、判断条件和不适用边界;不把建议包装成普遍规律。

每种模式都必须输出:假说或关键问题、研究如何可能推翻/限制它、最强反例或未知项、适用边界。争议评论以外禁止要求“打谁的脸”或情绪结盟;任何批评对象必须是可讨论的做法、规则或主张,不能把具体群体当靶子。

Step 3: 输出立场判定文件

文件路径:articles/[项目名]/01b_position.md

文件格式:

# 论证假说引擎输出

> 创建时间:[YYYY-MM-DD HH:MM]
> 项目名称:[项目名]

---

## 论证模式
- 文体:[来自 01_theme.md]
- 模式:[争议评论 / 解释分析 / 叙事观察 / 实用经验]

### 0. 风格内核对齐(如指定了风格)
> 本立场采用的作者判断方式:[作者首先看见什么 → 本文核心判断因此从哪个层面切入]
> 已避开的排除项:[风格内核中"自动排除"的角度]

### 1. 假说或关键问题
> [一句可被研究支持、推翻或限制的判断 / 问题]

### 2. 张力与读者所得
> [真正要解释的冲突、差异或任务,以及读者的新收获]

### 3. 争议对象(仅争议评论)
> [可讨论的主张、做法或规则;其他文体写“不适用”]

### 4. 最强反例、未知项与研究检验
> [什么证据会削弱本假说;研究必须寻找什么反证]

### 5. 适用边界
> [人群、条件、时间或场景边界]

Step 4: 返回摘要

✅ 立场引擎设计完成

【项目】:[项目名]
【核心判断】:[一句话核心判断]
【结盟对象】:[替谁说话]

📁 已保存:articles/[项目名]/01b_position.md

建议下一步:调用 research-expert 子代理进行素材调研

输入规范

使用 position-engine 子代理来生成立场文件。
项目名称:[项目名]
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. 1mo ago Changed · -9 lines · -12 tokens per session 503f128af750
  2. 1mo ago First seen · 115 lines · 59 tokens per session scan B 6e6a82766d36

Subscribe to this mod's changes

position-engine is an agent published in the GitHub repository dongbeixiaohuo/writing-agent (442 stars, last pushed 5d ago), licensed MIT. It adds 47 tokens to every session and 1,108 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.