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 zjp1997720/zhijian-skills --skill leadbookgit clone --depth 1 https://github.com/zjp1997720/zhijian-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/zjp1997720/zhijian-skills/leadbook)<a href="https://agentmods.dev/skills/zjp1997720/zhijian-skills/leadbook"><img src="https://agentmods.dev/badge/skills/zjp1997720/zhijian-skills/leadbook/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/zjp1997720/zhijian-skills/leadbook"><img src="https://agentmods.dev/badge/skills/zjp1997720/zhijian-skills/leadbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00136 | $0.05902 |
| Opus 5.5 | $0.00054 | $0.02361 |
| Sonnet 5.5 | $0.00027 | $0.01180 |
| Haiku 4.5 | $0.00014 | $0.00590 |
Grade A, and why
leadbook 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.
How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Leadbook
用于把一个商业主题写成独立、高质量、可公开传播的中文短书或白皮书。它继承 tech-book 的工程化写书骨架，但输出目标从技术出版改为普适商业认知与行动资产。
核心边界
- 正文必须独立成立：读者不购买任何产品，也能完整受益。
- 正文禁止硬 CTA：不写“加企微”“领取资料”“购买课程”“咨询我”等转化话术。
- 正文不绑定大鹏的分身系统、课程、定制、企业培训。
- 书外可以生成
distribution-note.md和private-domain-pack.md，但它们不得进入正式 PDF。 - 第一版默认写 30-50 页中文短书，不做 200 页大部头。
- Core 链路只依赖 Python 标准库，可完成脚手架、章节同步、Markdown 导出和质量检查。
- 通用模式默认使用公开 Web；小红书、公众号采集、Nowledge、Obsidian 和 Vault 都是可选 Provider，缺失时不得阻塞成书。
- 正式 PDF 可选使用
$kami的中文long-doc.html风格：暖纸底、ink-blue、克制 editorial 排版。 - 正文配图优先使用 Kami 信息图：结构、流程、对比、公式、清单。
$imagegen主要用于封面、章节扉页和书外分发图。
快速开始
新建一本书时，优先运行脚手架：
LEADBOOK_SKILL_DIR="/path/to/installed/leadbook"
python3 "$LEADBOOK_SKILL_DIR/scripts/scaffold_leadbook.py" \
"/path/to/books/超级个体商业操作系统" \
--title "超级个体商业操作系统" \
--content-profile methodology-book \
--voice-profile product-architect \
--author "大鹏"
脚手架会复制 assets/repo-template/，自动同步章节并生成带安全标记的标准 book repo。--force 只允许替换带 .leadbook-project.json 标记的既有 Leadbook 项目。之后按阶段工作，不要直接在聊天里散写全文。
完整成书属于耐久任务。每个 Phase 完成后运行 python3 scripts/leadbook-stage.py mark <phase>，把可恢复检查点写入 .leadbook-run.json。恢复时先运行 python3 scripts/leadbook-stage.py next，从第一个未完成阶段继续。具体规则见 执行检查点。
运行前按需读 运行时与隐私边界。Kami、小红书和公众号采集都是可选 Provider，不阻塞 Core 链路。
工作流
Phase 1：Book Brief
先写清楚这本书为什么存在。产出并维护：
BOOK_BRIEF.md：书名、副标题、目标、边界、完成标准。READER_PROFILE.md：读者是谁、处境、痛点、阅读动机。POSITIONING.md：核心主张、反常识判断、竞争性视角。book-state.yaml：章节状态、证据状态、输出状态和交付成熟度。VISUAL_PLAN.md：正文信息图、封面视觉、章节扉页和输出路径。IMAGEGEN_BRIEF.md：仅用于$imagegen位图视觉，不用于正文信息图。src/INTRODUCTION.md：读者可见开场。正式写作时删除模板标记，写入真实处境、问题重定义和阅读路径。
如果用户只给书名，先根据书名拟一版 brief，再指出缺口。不要把缺口脑补成事实。
BOOK_BRIEF.md 必须写清 content_profile、voice_profile 和 voice_anchor。书型决定结构，专家文风决定读者感受到“谁在说”，名人锚点负责把 Agent 快速拉进具体思考姿态。没有 voice profile 和 voice anchor，书会退化成资料汇编。
BOOK_BRIEF.md 还必须写清 opening contract 和 chapter rhythm。一本商业书不是把章节模板重复 6 次；它要先把读者带进一个真实处境、误判或反常识 tension，再说明这本书会怎样推进判断。没有 opening contract，正文很容易从第一页开始就像工作坊手册。
What ships with it
51 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 240 B
- assets/repo-template/assets/diagrams/.gitkeep 1 B
- assets/repo-template/assets/images/.gitkeep 1 B
- assets/repo-template/AUTHORITY_ACCOUNTS.md 2.4 KB
- assets/repo-template/BEHAVIOR_LEDGER.md 989 B
- assets/repo-template/BEHAVIOR_SEED_PLAN.md 1.3 KB
- assets/repo-template/bibliography.md 101 B
- assets/repo-template/BOOK_BRIEF.md 2.5 KB
- assets/repo-template/BOOK_SUMMARY.md 696 B
- assets/repo-template/book-state.yaml 2.0 KB
- assets/repo-template/CASE_LIBRARY.md 1.5 KB
- assets/repo-template/CLAIM_LEDGER.md 1.7 KB
- assets/repo-template/glossary.md 103 B
- assets/repo-template/IMAGEGEN_BRIEF.md 832 B
- assets/repo-template/OUTLINE.md 1.5 KB
- assets/repo-template/POSITIONING.md 311 B
- assets/repo-template/READER_PROFILE.md 395 B
- assets/repo-template/scripts/auto-seed-behavior.py 3.6 KB runs code
- assets/repo-template/scripts/check-backend-language.py 2.1 KB runs code
- assets/repo-template/scripts/check-evidence-feasibility.py 3.1 KB runs code
- assets/repo-template/scripts/check-leadbook.py 63 KB runs code
- assets/repo-template/scripts/export-kami-html.py 15 KB runs code
- assets/repo-template/scripts/export-markdown.py 4.1 KB runs code
- assets/repo-template/scripts/generate-kami-diagrams.py 16 KB runs code
- assets/repo-template/scripts/leadbook-stage.py 6.0 KB runs code
- assets/repo-template/scripts/prepare-pdf-visual-audit.py 6.9 KB runs code
- assets/repo-template/scripts/render-pdf.py 3.5 KB runs code
- assets/repo-template/scripts/sync-summary.py 17 KB runs code
- assets/repo-template/scripts/xhs-research.py 13 KB runs code
- assets/repo-template/SOURCE_MAP.md 3.0 KB
- assets/repo-template/src/SUMMARY.md 85 B
- assets/repo-template/templates/cases-template.md 309 B
- assets/repo-template/templates/chapter-template.md 1.4 KB
- assets/repo-template/templates/introduction-template.md 273 B
- assets/repo-template/templates/reader-workbook-template.md 627 B
- assets/repo-template/templates/refs-template.md 391 B
- assets/repo-template/templates/review-checklist.md 3.1 KB
- assets/repo-template/templates/self-assessment-template.md 278 B
- assets/repo-template/TRANSACTION_LEDGER.md 1.1 KB
- assets/repo-template/VISUAL_PLAN.md 1.1 KB
- evals/evals.json 3.6 KB
- LICENSE 1.0 KB
- references/evidence-gates.yaml 1.5 KB
- references/execution-checkpoints.md 1.7 KB
- references/kami-output.md 7.3 KB
- references/profiles.md 8.9 KB
- references/quality-gates.md 12 KB
- references/research-stack.md 11 KB
- references/runtime-and-privacy.md 1.7 KB
- scripts/scaffold_leadbook.py 5.7 KB runs code
- tests/test_leadbook.py 18 KB runs code
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 · 321 lines · 136 tokens per session scan A 5303876ec5c1
leadbook is a skill published in the GitHub repository zjp1997720/zhijian-skills (787 stars, last pushed 4d ago), licensed MIT. It adds 136 tokens to every session and 5,902 once invoked, about $0.0005 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 2026-08-30.
leadbook compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| leadbookzjp1997720/zhijian-skills | Skill | 787 | 4d ago | MIT | A | 136 | Codex |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| foundry-hosted-agent-validationmicrosoft/agent-framework | Skill | 15k | yesterday | MIT | A | 82 | Claude Code, Codex |
| skill-doc-deliverynyldn/claude-octopus | Skill | 4.4k | today | MIT | A | 29 | Claude Code |
| meta-web-to-pdf-briefingopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 45 | Claude Code, Codex |
| chat-complex-documentsvellum-ai/vellum-assistant | Skill | 1.5k | 2d ago | MIT | A | 90 | Claude Code, Codex |
| paper-readerhuangkiki/dailypaper-skills | Skill | 1.3k | 4d ago | Apache-2.0 | A | 135 | Claude Code, Codex |