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 makenotion/notion-cookbook --skill research-documentationgit clone --depth 1 https://github.com/makenotion/notion-cookbookWrote 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/makenotion/notion-cookbook/research-documentation)<a href="https://agentmods.dev/skills/makenotion/notion-cookbook/research-documentation"><img src="https://agentmods.dev/badge/skills/makenotion/notion-cookbook/research-documentation/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/makenotion/notion-cookbook/research-documentation"><img src="https://agentmods.dev/badge/skills/makenotion/notion-cookbook/research-documentation.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 | $0.00047 | $0.00778 |
| Opus 5 | $0.00023 | $0.00389 |
| Sonnet 5 | $0.00009 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
notion-research-documentation 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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- notion-research-documentation — 100% identical, 5 lines differ
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research & Documentation
Enables comprehensive research workflows: search for information across your Notion workspace, fetch and analyze relevant pages, synthesize findings, and create well-structured documentation.
Quick Start
When asked to research and document a topic:
- Search for relevant content: Use
Notion:notion-searchto find pages - Fetch detailed information: Use
Notion:notion-fetchto read full page content - Synthesize findings: Analyze and combine information from multiple sources
- Create structured output: Use
Notion:notion-create-pagesto write documentation
Research Workflow
Step 1: Search for relevant information
Use Notion:notion-search with the research topic
Filter by teamspace if scope is known
Review search results to identify most relevant pages
Step 2: Fetch page content
Use Notion:notion-fetch for each relevant page URL
Collect content from all relevant sources
Note key findings, quotes, and data points
Step 3: Synthesize findings
Analyze the collected information:
- Identify key themes and patterns
- Connect related concepts across sources
- Note gaps or conflicting information
- Organize findings logically
Step 4: Create structured documentation
Use the appropriate documentation template (see reference/format-selection-guide.md) to structure output:
- Clear title and executive summary
- Well-organized sections with headings
- Citations linking back to source pages
- Actionable conclusions or next steps
Output Formats
Choose the appropriate format based on request:
Research Summary: See reference/research-summary-format.md Comprehensive Report: See reference/comprehensive-report-format.md Quick Brief: See reference/quick-brief-format.md
Best Practices
- Cast a wide net first: Start with broad searches, then narrow down
- Cite sources: Always link back to source pages using mentions
- Verify recency: Check page last-edited dates for current information
- Cross-reference: Validate findings across multiple sources
- Structure clearly: Use headings, bullets, and formatting for readability
What ships with it
18 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.
- evaluations/basic-research.json 1.7 KB
- evaluations/README.md 4.2 KB
- evaluations/research-to-database.json 1.6 KB
- examples/competitor-analysis.md 8.4 KB
- examples/market-research.md 1.9 KB
- examples/technical-investigation.md 6.4 KB
- examples/trip-planning.md 3.7 KB
- reference/advanced-search.md 4.5 KB
- reference/citations.md 5.1 KB
- reference/comparison-format.md 871 B
- reference/comparison-template.md 973 B
- reference/comprehensive-report-format.md 1.1 KB
- reference/comprehensive-report-template.md 1.3 KB
- reference/format-selection-guide.md 3.1 KB
- reference/quick-brief-format.md 768 B
- reference/quick-brief-template.md 476 B
- reference/research-summary-format.md 841 B
- reference/research-summary-template.md 1.1 KB
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.
- 11d ago First seen · 97 lines · 47 tokens per session scan A 05175c669c1f
notion-research-documentation is a skill published in the GitHub repository makenotion/notion-cookbook (206 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 778 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…