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 skills add Lambenthan/paper-discipline-skills --skill paper-claude-md-bootstrapgit clone --depth 1 https://github.com/Lambenthan/paper-discipline-skillsWrote 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/skills/lambenthan/paper-discipline-skills/paper-claude-md-bootstrap)<a href="https://agentmods.dev/skills/lambenthan/paper-discipline-skills/paper-claude-md-bootstrap"><img src="https://agentmods.dev/badge/skills/lambenthan/paper-discipline-skills/paper-claude-md-bootstrap/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.
<a href="https://agentmods.dev/skills/lambenthan/paper-discipline-skills/paper-claude-md-bootstrap"><img src="https://agentmods.dev/badge/skills/lambenthan/paper-discipline-skills/paper-claude-md-bootstrap.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00129 | $0.01560 |
| Opus 5 | $0.00064 | $0.00780 |
| Sonnet 5 | $0.00026 | $0.00312 |
| Haiku 4.5 | $0.00013 | $0.00156 |
Grade A, and why
paper-claude-md-bootstrap 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 12d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paper-claude-md-bootstrap：新论文项目第一件事
核心理念
CLAUDE.md 是项目的"永久记忆"。第一天花 5–10 分钟写好，能省下后面每次会话开头 10 分钟的"我先解释下背景..."。 书里的真实数据：写过 CLAUDE.md 的项目和没写的，AI 的回应质量差距能拉开两个量级。
没有 CLAUDE.md 的项目 = 每次开会话都在和健忘的实习生从头讲一遍论文。
强制规则
进入新项目目录第一件事：用 ls 检查是否有 CLAUDE.md。
- 没有 → 立即停下当前任务，先和用户一起建一份
- 有但 < 30 行（空模板）→ 同上
- 有且完整 → 先 Read 完，再回答任何问题
不要"先做用户当下要的事，回头再补 CLAUDE.md"。回头永远不会到。
触发条件
满足任一条 → 触发：
- 用户说"开始写新论文"、"新开一个项目"、"帮我写第 X 章"
- 当前工作目录里没有
CLAUDE.md - 当前工作目录里有
CLAUDE.md但 < 30 行 - 用户说"我有篇论文..."、"我研究的是 XX" 而你不知道任何项目背景
强制流程
检测到无 CLAUDE.md
│
▼
告诉用户：「在动手之前，先花 5 分钟把 CLAUDE.md 建起来——
后面每次开会话能省下你重复解释的时间。」
│
▼
按下方"必问的六项"逐项问用户
（一次问一项，不要一口气列六个，避免用户视觉疲劳直接答"都行"）
│
▼
全部答完 → Write 工具落盘 CLAUDE.md
│
▼
回到用户最初的任务
必问的六项
| # | 字段 | 提问示例 |
|---|---|---|
| 1 | 研究主题 | "一句话说清你这篇论文研究什么、回答什么问题" |
| 2 | 投稿目标 | "投哪个期刊 / 会议？字数限制？格式（GB/T 7714 / APA / IEEE）？截稿日？" |
| 3 | 术语保护清单 | "哪些专业术语 / 缩写 / 自定义命名是必须保留的？防止我同义替换" |
| 4 | 文件结构 | "主稿在哪？参考文献在哪？图表在哪？draft / revision 怎么命名？" |
| 5 | 写作风格 | "第一人称还是第三人称？被动还是主动？紧凑还是详尽？" |
| 6 | 导师偏好 | "导师特别在意什么？逻辑线 / 引文密度 / 图表规范 / 口语化？有没有禁忌？" |
CLAUDE.md 模板
# [论文标题简称] 项目说明
## 研究主题
[一句话说清]
## 投稿目标
- 期刊 / 会议：[名称]
- 字数：[限制]
- 格式：[GB/T 7714 / APA / IEEE / ...]
- 截稿：[日期]
## 术语保护清单（不得被同义替换）
- [术语 1]：[全称 / 定义]
- [术语 2]：[...]
## 文件结构
- 主稿：[路径]
- 参考文献：[路径]
- 图表：[路径]
- 备份：[路径]
## 写作风格
- 人称：[第一 / 第三]
- 语态：[主动 / 被动 / 混合]
- 紧凑度：[紧凑 / 详尽]
## 导师偏好
- [X 老师特别在意：...]
- [禁忌：...]
## 工作纪律
- 改 .docx 前必先备份（见 paper-backup-before-word）
- 模糊任务先确认方案（见 paper-confirm-before-doing）
- 跨文件改前列保护术语（见 paper-protect-terminology）
❌ 反例
用户："帮我写一下第三章。" 错误：直接开始写——不知道是什么论文、什么风格、术语是哪些。 正确：「我看你这个目录还没有 CLAUDE.md。我们花 5 分钟先把它建起来，后面每次开会话都不用重新解释——可以吗？」
Rationalization Table
| 念头 | 现实 |
|---|---|
| "用户急着写第三章，先写完再补 CLAUDE.md" | 写完发现术语 / 风格 / 引用格式错了，全部重做 |
| "我可以从已有文件推断出风格" | 推断 ≠ 用户的真实偏好；导师偏好你推断不出来 |
| "另一个会话里告诉过我背景了" | 另一个会话不是这个会话，AI 没有跨会话记忆 |
| "CLAUDE.md 太正式，加重用户负担" | 6 个问题 ≤ 5 分钟 = 之后 50 个会话每次省 10 分钟 |
| "我先写一段试试效果，再让用户决定风格" | 你已经在用某种风格写了，用户的"反馈"会被你已写的内容锚定 |
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.
- 12d ago First seen · 152 lines · 129 tokens per session scan A 5541431afae6
paper-claude-md-bootstrap is a skill published in the GitHub repository Lambenthan/paper-discipline-skills (19 stars, last pushed 4mo ago), licensed MIT. It adds 129 tokens to every session and 1,560 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
secure-auth
Secure authentication patterns (OWASP, NIST). Use for login, registration, password reset, sessions, JWT, OAuth, MFA, passkeys.
academic-writing
Scholarly writing and research compliance. Use for CRediT, preregistration, Plan S, Nelson Memo, preprints, ORCID, LLM disclosure.
page-monitoring
Web page change detection, availability tracking, and RSS feed generation. Use to monitor changes, downtime, or make a feed.
web-archiving
Web archiving and retrieval via Wayback Machine and Archive.today. Use to preserve content, reach dead pages, or save evidence.
accessibility-compliance
Web accessibility patterns for news and academic sites. Use for WCAG audits, alt text, accessible data viz, and assistive tech.
one-way-door
Flags irreversible decisions before commit. Use for data models, infra, auth boundaries, API contracts, event schemas, CI/CD.