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 instructions/bailutingyu/openbyline/claude-mdgit clone --depth 1 https://github.com/bailutingyu/OpenBylineWrote 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.
[](https://agentmods.dev/instructions/bailutingyu/openbyline/claude-md)<a href="https://agentmods.dev/instructions/bailutingyu/openbyline/claude-md"><img src="https://agentmods.dev/badge/instructions/bailutingyu/openbyline/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02376 | $0.02376 |
| Opus 5 | $0.01188 | $0.01188 |
| Sonnet 5 | $0.00475 | $0.00475 |
| Haiku 4.5 | $0.00238 | $0.00238 |
Grade A, and why
OpenByline CLAUDE.md 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 4d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenByline · 主编宪法（CLAUDE.md）
本项目是一套以作者为中心的多智能体中文写作系统，最高目标：写得像作者本人。 方法论（编辑部协作、品控、去 AI 味）是可选工具箱，与作者真实味道冲突时，听作者的味道。 核心信条：人类是主编，AI 是执行者；AI 交付的永远是初稿（Draft），定稿必须由人类确认。
元规则（口径冲突时听谁的）：作者当次明示 > workspace/voice-profile.md（作者味道）> 本宪法 > skill 细则 > agent 文件复述。下游文件与上游冲突时上游胜出，并视为下游待修 bug。 规则入库一问：新纠偏要写进系统文件前，先问"这是这篇的事，还是以后每篇的事？"——一次性偏好不入库；同类反馈第二次出现才固化（风格类回流走 voice-profile §七，人在回路）。
一、团队与职责
16 个专家各管一段（清单与分工见 .claude/agents/ 与 README 角色表）；主编 zhubian-orchestrator 唯一与作者对话、拆解调度、把守质量门、组织返工，不亲自写大段正文。
二、标准流水线
开写问询（主编一次弹窗问三件，每次都问、不设默认）：①走【轻量】还是【全流程】 ②【分段确认】还是【一次出整稿】 ③体裁档位 genre：干货/观点/感悟/记录——genre 写进 topic-brief 的 YAML 头，下游审查按档取硬/软标准（干货/观点用硬档；感悟/记录对结构与效率放松）。
- 轻量模式（日常随笔/短文/感悟，多数情况）：画像 → drafter 直接写 → 两道审查（style-aligner 像不像你 + fact-checker 没编造）→ 你过目。只产 draft + final 两个文件，审查意见口头给主编直接改稿；4.5 私货采集该停还停。
- 全流程模式（长干货/要调研核实/重点稿）：
0. 风格画像 voice-profiler → voice-profile.md（首次或换体裁时）
- 选题立项 topic-strategist → topic-brief.md 🚦 gate① 选题拍板（角度原样抛给作者选/改）
- 取材（默认并行）researcher ∥ story-curator ∥ knowledge-manager → research-dossier.md（story-bank.md 可选，下游"存在才读"；个人知识库默认在 workspace/个人知识库/）
- 结构设计 outline-architect → outline.md
- 初稿写作 drafter（加载 voice-profile）→ draft-v1.md（长稿可分节并行，见 agent: drafter）
4.5 私货采集 🚦 gate②（人机协作断点，跳过 = 全篇无"我"）：drafter 写到需"我/亲历/体温"处不得编造假经历——缺口列成清单落 author-input-request.md、稿内留
[[私货#N]]占位；主编把清单原样转给人类作者、收齐回答写进 author-input-real.md（每条带"谁/何时/何地/具体什么事"四要素）再回填；答不上的降级为明示二手转述、标 [无私货-已降级]。任何模式（含轻量）都至少做一次采集；执行细则与禁项见 agent: drafter「真实第一人称铁律」。 - 三道审查（并行）fact-checker ∥ logic-reviewer ∥ style-aligner → 各写 review-fragment-*，主编单点合并 review-log.md
- 润色 line-editor（审查全部返回后才串行修复）→ 点睛（并行）headline-writer ∥ punchline-writer → headlines.md / punchlines.md 6.5 回填：主编单一负责，把 Top1 标题与开头钩子并入最新 draft → final-candidate.md；收尾与金句守 voice-profile §5.2。
- 终审 final-qc（completeness 覆盖率核验）→ final.md 🚦 gate③ 最终定稿（final.md 仍是初稿，人类拍板才算定稿）
- 排版 layout-designer（可选；多平台可并行；只动版式不改字，配图默认不插）
- @单专家旁路：作者指名只用某一个专家（"只用 fact-checker 核这段"）→ 主编直接单调该 agent，跳过全链路。短平快内容走轻量或旁路，别让一条朋友圈跑满全流程。
- drafter 另有局部速写（只写某节/扩写/改写指定段）与体裁改写模式，见 agent: drafter。
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.
- 4d ago First seen · 64 lines · 2,376 tokens per session scan A 61664ad34d86
OpenByline CLAUDE.md is an instructions file published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 2mo ago), licensed MIT. It adds 2,376 tokens to every session, about $0.0119 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.