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-lookupnpx skills add BackendGameSetMatch/sourcebook --skill sourcebook-lookupgit clone --depth 1 https://github.com/BackendGameSetMatch/sourcebookWrote 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/backendgamesetmatch/sourcebook/sourcebook-lookup)<a href="https://agentmods.dev/skills/backendgamesetmatch/sourcebook/sourcebook-lookup"><img src="https://agentmods.dev/badge/skills/backendgamesetmatch/sourcebook/sourcebook-lookup.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 | $0.00080 | $0.00545 |
| Opus 5 | $0.00040 | $0.00272 |
| Sonnet 5 | $0.00016 | $0.00109 |
| Haiku 4.5 | $0.00008 | $0.00055 |
Grade A, and why
sourcebook-lookup 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 5d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Documentation Lookup
This project maintains structured AI-readable documentation in /docs/ai/.
Consult these docs BEFORE making assumptions about how systems work, what
conventions exist, what has already been decided, or which APIs we depend on.
How to search
Run the lookup script from this skill's directory:
python .claude/skills/sourcebook-lookup/scripts/lookup.py search <keywords>
python .claude/skills/sourcebook-lookup/scripts/lookup.py list [systems|processes|decisions|apis]
python .claude/skills/sourcebook-lookup/scripts/lookup.py read <path>
python .claude/skills/sourcebook-lookup/scripts/lookup.py bundle <scope>
python .claude/skills/sourcebook-lookup/scripts/lookup.py glossary [term]
python .claude/skills/sourcebook-lookup/scripts/lookup.py conventions
python .claude/skills/sourcebook-lookup/scripts/lookup.py decisions [--status active]
python .claude/skills/sourcebook-lookup/scripts/lookup.py index
python .claude/skills/sourcebook-lookup/scripts/lookup.py log
Run it with no arguments to see the full command list.
When to consult docs
- Before modifying core service or library code - search for the system or module
- Before integrating a new external API - load the bundle covering API references
- Before modifying any build, deploy, or infrastructure code - load the bundle covering it
- Before changing release workflows - read the relevant process doc
- Before suggesting an architectural approach -
list decisions - When encountering unfamiliar internal terms -
glossary <term> - When unsure about constraints -
conventions
Bundle names are project-specific. Passing an unknown scope to bundle
prints the list this project actually defines, so check there rather than
guessing a name.
Important rules
- The
decisions/directory contains Architectural Decision Records. Always check before proposing approaches. - The
conventions.mdfile contains hard constraints. Never violate these. - If docs seem stale (check
last_verifieddates), flag it rather than trusting outdated information.
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.
- 5d ago First seen · 55 lines · 80 tokens per session scan A a009d47f0515
sourcebook-lookup is a skill published in the GitHub repository BackendGameSetMatch/sourcebook (3 stars, last pushed 23d ago), licensed MIT. It adds 80 tokens to every session and 545 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。.
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。.
data_analysis
基于已确认数据执行可审计的数学计算和描述统计。.
coding
编写并运行 Python 代码，验证脚本逻辑和输出。.