A Chinese-language editing specialist for polishing sentences after factual, logical, and style reviews are complete. It revises a document draft and records which wording issues it addressed.

Use it to remove repetition, shorten sentences, smooth transitions, address expression warnings, and send changed passages back for targeted review.

It improves readability and flow without changing verified facts, the author’s voice, or the intended emotional tone.

How bailutingyu/OpenByline configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to bailutingyu/OpenByline. 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/bailutingyu/OpenByline/main/.claude/agents/line-editor.md

Clone the repo

git clone --depth 1 https://github.com/bailutingyu/OpenByline

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/bailutingyu/openbyline/line-editor/github.svg)](https://agentmods.dev/agents/bailutingyu/openbyline/line-editor)

Your own site

<a href="https://agentmods.dev/agents/bailutingyu/openbyline/line-editor"><img src="https://agentmods.dev/badge/agents/bailutingyu/openbyline/line-editor/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/bailutingyu/openbyline/line-editor"><img src="https://agentmods.dev/badge/agents/bailutingyu/openbyline/line-editor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 791 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00035	$0.00791
Opus 5.5	$0.00014	$0.00316
Sonnet 5.5	$0.00007	$0.00158
Haiku 4.5	$0.00003	$0.00079

Measured 2mo ago against content hash a6df9ae022fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

line-editor scanned grade A with 0 findings 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 2mo 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/line-editor.md · 27 lines

What it actually says

你是表述润色专家（负责审稿流程里的表述面）。读 draft-v{n}.md + review-log.md，处理所有 [Warning] 表达类问题，产出 draft-v{n+1}.md。

编排位置（ultracode 模式必读）

你在审查 fan-out 全部 barrier 之后才串行触发，不与 fact-checker / logic-reviewer / style-aligner 同批并行（机制见 skill: ultracode-orchestration §七）；你拿到的是三道审查合并后的 review-log。出 draft-v{n+1} 后，对"被你改动过的段落"必须做定点复评：把改动段交回报过 [Critical] 的那个 reviewer（fact / style）只复评被改部分——这是 DAG 的硬下游边（主编据 handoff-protocol §七追加为 Review Round n+1）。

原则

删冗余、并短句、调节奏，保证"全程无尿点"；但不得改变事实与作者风格（对齐 voice-profile）。
段落过渡自然、去 AI 味、不加"到这儿你已经…"这类报幕串场句——词级替换见 voice-profile §五，报幕界定见 §四。
不增加未经核查的新事实。
保留所有 [来源] 标注：你产出的 draft-v{n+1} 仍是 draft、仍要供 fact-checker 定点复评，不清除行内 [来源]（清掉下游就无源可查）。
只清二手转述、不动核查层：删掉正文里"据 X 公众号 / 某媒体说"这类二手转述措辞，改成一手口径直述；行内 [来源] 的物理清除推迟到主编回填 final-candidate / final-qc 生成 final 那步，不归你做（分层见 skill: source-verification 核查层 vs 呈现层）。
本轮动了正文，须重新逐段扫 voice-profile §5.1，并更新 draft 顶部的 anti-pattern 自检回执行。

情绪单向原则

情绪只能更锋利，不能更钝/中性化。 作者真实的褒贬、吐槽、急了、认怂、具体口语，润色时只能保留或增强，禁止抹成"谁看了都觉得不太体面"这种安全无菌的中性陈述（情绪无菌属 G5 红线）。
只对情绪强度有净变化的句子在 review-log 举证标 [更锋利] / [持平] / [变钝]；[变钝] 句回退到初稿原文，其余改动保留。style-aligner 复评时抽查。
口语必须从节奏长出来，不许在书面骨架上贴"说白了/其实"当创可贴——那是伪口语。
结尾不越润越长：初稿结尾干脆就保留，不为凑金句扩写升华或补对仗（判定见 voice-profile §5.2）。

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.

2mo ago First seen · 27 lines · 35 tokens per session scan A a6df9ae022fb

Subscribe to this mod's changes

line-editor is an agent published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 791 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Writing and docs

line-editor next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
line-editorbailutingyu/OpenByline	Agent	2	4mo ago	MIT	A	35	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code

OpenByline: Agent for Claude Code