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 knowledge-capturegit 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/knowledge-capture)<a href="https://agentmods.dev/skills/makenotion/notion-cookbook/knowledge-capture"><img src="https://agentmods.dev/badge/skills/makenotion/notion-cookbook/knowledge-capture/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/knowledge-capture"><img src="https://agentmods.dev/badge/skills/makenotion/notion-cookbook/knowledge-capture.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 | $0.00058 | $0.00872 |
| Opus 5.5 | $0.00023 | $0.00349 |
| Sonnet 5.5 | $0.00012 | $0.00174 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
notion-knowledge-capture 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 19d 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-knowledge-capture — 100% identical, 246 lines differ
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge capture
Preserve useful knowledge from the conversation in the requested Notion location. Keep decisions, rationale, technical details, and unresolved questions faithful to what was actually said.
Workflow
- Identify the material and outcome. Use the conversation or supplied notes. Separate agreed decisions from proposals; do not invent owners, dates, consensus, or missing steps. Ask only for missing information that changes the content or destination. A draft request produces a draft without publishing.
- Choose a structure. Use the patterns below as needed, omitting empty sections. Match length to the material and requested audience. Preserve exact commands and configurations; label any suggested additions.
- Resolve the destination. Fetch a supplied page or database directly. Search only when the destination or an existing document needs discovery. Update an existing document when the material belongs to the same topic; create a page when it needs a distinct purpose or the user requests one. Preserve unrelated content and flag conflicting decisions instead of silently replacing them. For material revisions, retain prior rationale and a dated change note when useful for understanding how the knowledge evolved.
- Save and connect. For a database, fetch its schema once and use its actual data source, properties, options, and relations. Suggested schemas below are design examples, not required properties. Add source and related-page links. Update hub navigation, categories, or bidirectional links when requested or part of the established destination convention; avoid unrelated reorganization.
- Verify and report. Check the write result and return the created or updated page link with a brief description. Read back changed content when the response does not establish that the intended update succeeded. Report unresolved gaps.
Content patterns
| Content | Useful structure |
|---|---|
| Concept or reference | Definition, scope, examples, related material |
| How-to | Prerequisites, numbered steps, verification, troubleshooting |
| Decision record | Context, decision, alternatives, rationale, consequences |
| FAQ | Question, direct answer, explanation or examples when needed |
| Meeting summary | Outcomes, decisions, open questions, actions |
| Learning or post-mortem | What happened, contributing causes, lessons, actions |
What ships with it
16 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/content-types.json 818 B
- evaluations/conversation-to-wiki.json 1.0 KB
- evaluations/decision-record.json 1.2 KB
- evaluations/draft-without-connection.json 696 B
- evaluations/README.md 2.1 KB
- evaluations/update-existing.json 847 B
- examples/conversation-to-faq.md 16 KB
- examples/decision-capture.md 3.5 KB
- examples/how-to-guide.md 2.8 KB
- reference/database-best-practices.md 3.3 KB
- reference/decision-log-database.md 2.5 KB
- reference/documentation-database.md 3.6 KB
- reference/faq-database.md 2.7 KB
- reference/how-to-guide-database.md 1.6 KB
- reference/learning-database.md 1.8 KB
- reference/team-wiki-database.md 1.4 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.
- 19d ago Changed · -125 lines · +8 tokens per session ba2a680872ec
- 1mo ago First seen · 201 lines · 50 tokens per session scan A 42e8c7634c25
notion-knowledge-capture is a skill published in the GitHub repository makenotion/notion-cookbook (220 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 872 once invoked, about $0.0002 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.