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 skills/backendgamesetmatch/sourcebook/sourcebook-bundlenpx skills add BackendGameSetMatch/sourcebook --skill sourcebook-bundlegit clone --depth 1 https://github.com/BackendGameSetMatch/sourcebookWhat 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 | $0.00085 | $0.00317 |
| Opus 5 | $0.00043 | $0.00159 |
| Sonnet 5 | $0.00017 | $0.00063 |
| Haiku 4.5 | $0.00009 | $0.00032 |
Grade A, and why
sourcebook-bundle 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.
What it actually says
AI Documentation Bundle Loader
Load a context bundle to get full knowledge about a specific domain.
Usage
Run the bundle assembler with a scope name:
python .claude/skills/sourcebook-bundle/scripts/lookup.py bundle $ARGUMENTS
Available bundles
Bundles are whatever this project defines in /docs/ai/bundles/ — the set
differs per project, so do not assume a name exists. To see the real list,
run the command with any unknown scope; it prints the available bundles:
python .claude/skills/sourcebook-bundle/scripts/lookup.py bundle list-me
A fresh sourcebook init starts you with ci (CI/CD pipelines, build and
deployment), apis (API references and related decisions), onboarding
(system cards + glossary + conventions), and backend (backend services,
jobs, data pipelines). Projects add, rename, and remove these freely.
The output is a single markdown document with all relevant docs assembled and ready for use as context.
What ships with it
1 file 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.
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 · 37 lines · 85 tokens per session scan A 6875bbed2396
sourcebook-bundle is a skill published in the GitHub repository BackendGameSetMatch/sourcebook (3 stars, last pushed 20d ago), licensed MIT. It adds 85 tokens to every session and 317 once invoked, about $0.0004 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 skills, from other repositories
pptx
从论文、大纲或结构化文本生成 PowerPoint (.pptx) 演示文稿。Use when 用户需要把一篇论文/文章/大纲做成幻灯片、slides、演示文稿、PPT、deck。Don't use when 只需纯文本总结、生成 Word/PDF、或修改已有 pptx 的单个像素级样式。.
ai-style
当任务是用中文撰写或改写面向读者的文案（产品发布稿、公众号文章、邮件、README 等）， 或用户反馈文字「AI 味太重」「不像人写的」时，加载本 Skill。.
curly-quote-sft
Skill "curly-quote-sft" from bojieli/ai-agent-book, covering 中文技术文档符号与引用规范, 何时加载, 符号定义, 决策优先级 and 正反例约束.
triage
你是当前任务的分诊协调者。先识别用户的全部目标、顺序依赖和验收条件，再按 “事实检索 → 计算/执行 → 写作”顺序逐步请求切换到需要的专业能力。不要替专业 能力完成它的工作，也不要在信息缺失时臆造结果。.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
coding
编写并运行 Python 代码，验证脚本逻辑和输出。.