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 rongarede/claude-skills-research --skill nb-querygit clone --depth 1 https://github.com/rongarede/claude-skills-researchWrote 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/rongarede/claude-skills-research/nb-query)<a href="https://agentmods.dev/skills/rongarede/claude-skills-research/nb-query"><img src="https://agentmods.dev/badge/skills/rongarede/claude-skills-research/nb-query/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/rongarede/claude-skills-research/nb-query"><img src="https://agentmods.dev/badge/skills/rongarede/claude-skills-research/nb-query.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 | $0.00113 | $0.01988 |
| Opus 5 | $0.00056 | $0.00994 |
| Sonnet 5 | $0.00023 | $0.00398 |
| Haiku 4.5 | $0.00011 | $0.00199 |
Grade A, and why
nb-query scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NotebookLM 深度查询（带引用溯源 + 核查 + 本地图片溯源）
对 NotebookLM Skill 的增强 Wrapper，采用超富集模式查询。
核心理念
- 超富集查询：不追求言简意赅，尽可能搜集资料，宁多勿少
- 过程可追溯：所有中间产物存储到工作目录，支持断点续查
- 外部核查：强制使用外部检索验证关键信息的准确性和时效性
- 本地图片溯源：不依赖 NotebookLM 的图片输出，从本地文章存档中提取正确的图片
工作目录结构
~/Downloads/nb-query-<主题关键词>-<日期>/
├── 00-metadata.md # 任务元信息
├── 01-raw-response.json # NotebookLM 原始 JSON 输出
├── 02-raw-answer.md # 原始回答（带引用序号）
├── 02-raw-answer-with-images.md # 带图片的回答
├── 03-citation-map.json # 序号 → 标题映射
├── 03-title-stats.json # 文章统计
├── 03-citation-table.md # 引用对照表（含链接）
├── 03.1-link-results.json # 链接映射结果
├── 03.5-all-images.json # 原始图片列表
├── 03.5-image-mapping.json # 过滤后的图片映射
├── 04-fact-verification.md # 外部检索核查结果
└── 05-final.md # 最终输出
执行流程
阶段 -1：同步知识库（BLOCKING）
每次查询前，先确保本地文章存档与 NotebookLM 同步：
/sync-notebooklm-kb
阶段 0：初始化与依赖检查
# 创建工作目录
WORK_DIR=~/Downloads/nb-query-<topic-in-english>-$(date +%Y%m%d)
mkdir -p "$WORK_DIR"
# 检查本地文章存档依赖
python scripts/check_articles_dir.py
命名规范：主题用英文/拼音，如 nb-query-ai-tools-workflow-20260115
写入 00-metadata.md：任务元信息（时间、查询主题、笔记本、状态）
阶段 1：准备阶段
# 确认笔记本上下文
notebooklm status
# 获取 source 列表（必须用 --json）
notebooklm source list --json > /tmp/nb_sources_raw.json
# 构建映射表
python scripts/build_source_mapping.py
阶段 2：超富集查询
查询 prompt 模板（强制详细 + 禁止图片输出）：
请针对以下问题，提供**尽可能详尽、全面**的回答：
{用户的原始问题}
要求：
1. 不要精简：宁可冗长也不要遗漏
2. 超富集搜集：所有相关内容都整合进来
3. 多角度覆盖：从不同维度汇总信息
4. 保留细节：具体数字、日期、案例都保留
5. 标注引用：每个信息点都标注 [1], [2] 等
6. 不做总结性压缩
7. 禁止输出图片链接
8. 标记配图位置：用 <!-- IMAGE_PLACEHOLDER: [引用号] --> 标记
notebooklm ask "..." --json > "$WORK_DIR/01-raw-response.json"
从 JSON 提取 answer 写入 02-raw-answer.md
阶段 3：生成引用对照表
WORK_DIR="$WORK_DIR" python scripts/generate_citation_table.py
阶段 3.1：添加外部链接
WORK_DIR="$WORK_DIR" python scripts/add_article_links.py
输出：03-citation-table.md（含链接）
What ships with it
6 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.
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 · 210 lines · 113 tokens per session scan A 400f8bbe0278
nb-query is a skill published in the GitHub repository rongarede/claude-skills-research (2 stars, last pushed 5mo ago), licensed MIT. It adds 113 tokens to every session and 1,988 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 2026-08-31.
Other skills, from other repositories
tencent-docs
A skill for creating, reading, editing, searching, and managing Tencent Docs, an online document and spreadsheet service.
government-writing
A skill for writing formal Chinese government documents, including notices and opinions, in the required official format.
ima-skills
Tencent IMA OpenAPI skill for notes and knowledge-base operations. Use after the user connects IMA in Pinvou Plugin Center.
lark-base
A guide for managing Lark Base, Feishu's spreadsheet-like database and workspace tool. It covers tables, fields, records, views, formulas, forms, dashboards, applications, workflows, and permissions.
visualizer
A skill for turning structured data, spreadsheets, and business metrics into HTML charts and dashboards using Chart.js, a JavaScript charting library.
lark-doc
A tool for working with documents, wikis, images, attachments, whiteboards, and notes in Feishu, also called Lark. It supports reading, creating, editing, exporting, and restoring document content.