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 Grey-Iris/easy-notion-mcp --skill notion-recipesgit clone --depth 1 https://github.com/Grey-Iris/easy-notion-mcpWrote 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/grey-iris/easy-notion-mcp/notion-recipes)<a href="https://agentmods.dev/skills/grey-iris/easy-notion-mcp/notion-recipes"><img src="https://agentmods.dev/badge/skills/grey-iris/easy-notion-mcp/notion-recipes/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/grey-iris/easy-notion-mcp/notion-recipes"><img src="https://agentmods.dev/badge/skills/grey-iris/easy-notion-mcp/notion-recipes.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 | $0.00068 | $0.01454 |
| Opus 5 | $0.00034 | $0.00727 |
| Sonnet 5 | $0.00014 | $0.00291 |
| Haiku 4.5 | $0.00007 | $0.00145 |
Grade A, and why
notion-recipes 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notion Recipes
Use these recipes with easy-notion's MCP tools, or through the claude.ai connector when the equivalent tools are enabled. Recipe 2 (repair and find-replace) also works through the easy-notion CLI skill in skills/easy-notion-cli/. Recipe 1 does not: it needs create_database, source-block lookup with search_in_page, and structured database filters, and the current CLI surface does not expose that full workflow.
Recipe 1: Meeting Notes To Action Items
Turn a meeting-notes page or pasted notes into deduplicated rows in an Action Items database.
Safety boundary: Recipe 1 is re-run-safe and idempotent because Item Key stores the source line's stable Notion identity (<pageId>:<blockId>), not the action wording.
- Create the Action Items database once with
create_databaseunder the user-selected parent page:
{
"parent_page_id": "<parent page ID>",
"title": "Action Items",
"schema": [
{ "name": "Name", "type": "title" },
{ "name": "Item Key", "type": "rich_text" },
{ "name": "Owner", "type": "rich_text" },
{ "name": "Due", "type": "date" },
{ "name": "Status", "type": "status" },
{ "name": "Flags", "type": "multi_select" },
{ "name": "Source", "type": "rich_text" }
]
}
- Read or receive the meeting notes. Extract only discrete action items.
- For each item, derive these properties:
Name: the action text.Owner: the named assignee, or blank.Due: the stated date as ISOYYYY-MM-DD, or blank.Item Key: the source line's stable identity, formatted as<sourcePageId>:<sourceBlockId>.Source: the meeting title plus date. Do not stash flags here.Status:Not started.Flags: addneeds-ownerif no owner, andneeds-dueif no due date. These aremulti_selectvalues, not text inSource.
- Resolve
sourceBlockIdwithsearch_in_page.read_pagereturns markdown without block IDs. For a Notion-page source, callread_pageto extract items, then for each item callsearch_in_pagewith a verbatim, distinctive substring of that item's original source line. Use thematches[].block_idwhose text is that source line. If several blocks match, use a longer verbatim substring to isolate one block. For pasted notes, first save them as a Notion page withcreate_page, then proceed throughsearch_in_page; do not rely on block IDs fromcreate_page, which returns only{id,title,url}. If one source line contains multiple distinct actions, append a stable ordinal suffix in source order, such as:1or:2, to keep keys unique. - Dedupe before insert. For each item, call
query_databasewith this exact filter shape:
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 · 109 lines · 68 tokens per session scan A 2a02cdd2ab4c
notion-recipes is a skill published in the GitHub repository Grey-Iris/easy-notion-mcp (51 stars, last pushed 10d ago), licensed MIT. It adds 68 tokens to every session and 1,454 once invoked, about $0.0003 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
jira-upload-chat-log
Use this skill to export and upload the current chat conversation as a markdown file attachment to a JIRA ticket for later review and documentation.
aside-notion
Read this skill when you need to use Notion. Don't have to open a browser tab.
wechat-article-scraper
A batch tool for downloading WeChat public-account articles from their URLs as Markdown files. It also downloads the articles' images and links them locally.
md-anything
Convert files, URLs, and media to Markdown with a local-first CLI and MCP server. Use mda doctor to see what this machine can actually extract well.
gptaria-publish-project
Publish a project brief to GPTaria from your own AI via a €10 Pro order, then pull the builder responses over MCP and work on them in your own assistant. Use when a client has worked out an idea — often already developed with an AI in this editor — and wants to post it as a GPTaria project and collect prototype…
extract-straight-bill-of-lading-data
Extract structured fields from straight bill of lading documents.