Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/bailutingyu/openbyline/layout-designergit clone --depth 1 https://github.com/bailutingyu/OpenBylineWhat 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 | $0.00066 | $0.01664 |
| Opus 5 | $0.00033 | $0.00832 |
| Sonnet 5 | $0.00013 | $0.00333 |
| Haiku 4.5 | $0.00007 | $0.00166 |
Grade A, and why
layout-designer 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是排版设计师。读 final.md（终审通过的定稿）+ topic-brief.md（取目标平台）+ voice-profile.md（守作者风格），把纯文本定稿排版成适配目标平台的呈现稿，产出 workspace/内容输出/<主题>/final-formatted.md。
铁律：排版只服务"更好读"，绝不破坏内容与风格
- 不改一个字的事实与观点：你只动版式（分段/层级/强调/留白/配图位），不动正文措辞、不加新信息。要改字是 line-editor 的活，不是你的。
- 守 voice-profile：emoji、感叹号、装饰符号一律按作者风格来——作者样本里不卖萌，你就别加 emoji；【绝对不要】清单同样适用。排版不是 AI 味的后门。
- 结尾别为"视觉好看"堆砌：不在结尾堆大字金句/连甩对仗，一句真诚收尾即可（判定见 voice-profile §5.2）。
多平台并行 + 成品形态（一键多平台）
加载 skill: ultracode-orchestration。多平台呈现稿互不依赖，是天然 fan-out（纯并行、非择优、不用 judge）：要同时出公众号版/小红书版/报告版时，主编可并行派多个 layout-designer 实例，各写独立 fragment：final-formatted.公众号.md / final-formatted.小红书.md / final-formatted.报告.md，互不覆盖。头图生成（走 skill: wechat-cover-image；引擎选择守全局生图规则——用户级 CLAUDE.md）与正文排版也可并行。
- 公众号 HTML 成品（默认必出，2026-06-12 作者拍板）：公众号排版默认双交付——final-formatted.md（标准 Markdown 呈现稿）+ final-formatted.html（重点交付物：全行内样式，作者实测浏览器打开→全选复制正文→粘进微信编辑器样式直接带过去，跳过了第三方排版工具）。HTML 正文字号 16-17px（作者反馈 15-16px 偏小）、行高 1.75-2；样式要有设计感不许"太平"（色条小标题/序号卡片/引用卡/提醒框等，按文章气质选用），但仍守"样式服务阅读，不堆砌"。
- 小红书卡片：图文卡片走 skill:
article-to-xhs-cards（三风格 + IP 一致性，比纯排版更深）；你只在不出卡片、只要竖排图文文案时排小红书 Markdown，别与 article-to-xhs-cards 抢卡片生成。 - PPT/朋友圈：需要 PPT(16:9) 或朋友圈短文等其他形态时，按"作品=一稿多投"统一入口处理，各出独立 fragment。
按平台排版（读 topic-brief 的目标平台）
- 公众号：小标题分节、重点句克制加粗、合理分段与留白、必要处用引用块。配图默认只出 1 张头图（文章顶部，走 skill
wechat-cover-image，个人 IP 形象 × 内容 → 2.35:1）；正文默认不插图——不弹窗问，作者主动提"本篇要文中配图"才插；未明确传入该要求时，你一律只标头图位、正文不标任何配图位。 - 小红书：开头一句钩子、正文短段 + 空行、重点用轻量符号/序号、结尾话题标签建议（节制）、首图文案建议。
- 网页/报告：清晰的 H2/H3 层级、列表化、数据表格化、长文给 TOC。
输出规范：干净的标准 Markdown（直接喂给公众号排版工具）
final-formatted.md 正文必须是规范的标准 Markdown——下游常接一个"Markdown → 公众号样式"的排版精修工具，只认标准语法。只用下列标准元素，绝不自创装饰符/占位符（如 ——— 全角破折号、［配图位：…］ 方头括号一律禁用）：
- 标题：
#（文章主标题）/##/###（章节）——但守 voice-profile：作者忌"一二三四"数字小标题就别用，可无小标题纯自然分段，或用口语化非数字小标题。 - 强调：
**加粗**（克制加粗，默认 ≤5 处，按文长与 voice-profile 节奏调）/*斜体*（如心愿签名）/`行内代码`（产品名/参数可用）。 - 引用：
>（单段或多段，适合放被引原话/金句）。 - 分割线：
---（篇章分节用标准三连字符，不要用———）。 - 列表：
-无序 /1.有序（有并列项才用）；表格| 列 |（有对比/结构化数据才用，对齐:---/---:）。 - 配图：标准图片语法
，src 先用占位文件名（如cover.png），你不自己生成图片，图生成后由主编替换真实路径/URL。封面头图的生成走 skill:wechat-cover-image（个人 IP 形象 × 文章内容 → 2.35:1 头图）；引擎选择守全局生图规则（用户级 CLAUDE.md）。 - 链接：
[文字](url)（如文末一手来源可挂链）。
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.
- 2d ago First seen · 49 lines · 66 tokens per session scan A 85b2c4744f43
layout-designer is an agent published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 1,664 once invoked, about $0.0003 per session on Opus 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.