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 avizmarlon/agent-skills --skill notion-apigit clone --depth 1 https://github.com/avizmarlon/agent-skillsWrote 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/avizmarlon/agent-skills/notion-api)<a href="https://agentmods.dev/skills/avizmarlon/agent-skills/notion-api"><img src="https://agentmods.dev/badge/skills/avizmarlon/agent-skills/notion-api/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/avizmarlon/agent-skills/notion-api"><img src="https://agentmods.dev/badge/skills/avizmarlon/agent-skills/notion-api.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 | $0.00079 | $0.02406 |
| Opus 5 | $0.00039 | $0.01203 |
| Sonnet 5 | $0.00016 | $0.00481 |
| Haiku 4.5 | $0.00008 | $0.00241 |
Grade A, and why
notion-api scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Avoid external dependencies — use Python stdlib only (e.g., `urllib`, `json`, `time`) How it starts
The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notion REST API — Direct wrapper for batch operations
When working with Notion programmatically, use the REST API (not the MCP) for any batch-shaped work. MCP implementations (like notion-search) typically have hard limitations (25-result caps, no real pagination) that make batch operations tedious. The REST API handles 100+ rows in seconds with auto-pagination.
When to use REST API vs MCP
| Operation | Use |
|---|---|
| Read 1 page, update 1 page, search for a page | MCP OK |
| Add a comment, create a single inline note | MCP OK |
| Query an entire database (any size), with filters and pagination | REST API |
| Batch update N pages (rename, retag, restructure) | REST API |
| Audit/scan/inventory a database | REST API |
| Replicate page body blocks | REST API |
| Upload files/images programmatically | REST API (MCP cannot) |
| Create a new database programmatically | REST API |
| Move pages by re-creating under a new parent | REST API |
| Any operation touching ≥3 rows | REST API |
If you find yourself calling MCP twice for the same data, switch to the REST API.
Python wrapper pattern
Create a thin self-contained wrapper around the Notion REST API. This wrapper should:
- Handle authentication via environment variable (e.g.,
NOTION_API_KEYorNOTION_TOKEN) - Provide auto-pagination for list endpoints (use
start_cursor/has_moreloops) - Include retry logic with exponential backoff for rate limits (HTTP 429) and transient errors (5xx)
- Throttle writes to respect Notion's published rate limit (~3 req/s)
- Expose CRUD functions for pages, databases, blocks, and comments
- Include property builders for clean schema construction (title, rich_text, select, date, etc.)
- Avoid external dependencies — use Python stdlib only (e.g.,
urllib,json,time)
Canonical imports (your wrapper should export)
# Core CRUD
get_page, create_page, update_page, archive_page
get_database, create_database, update_database
# Querying (query_db_all should auto-paginate)
query_database, query_db_all
# Blocks
get_block, list_block_children, list_block_children_all
append_block_children, update_block, delete_block
# Search and metadata
search, search_all, list_users_all, get_user, whoami
create_comment, list_comments_all
# File uploads (for image/attachment re-hosting)
file_upload_create, file_upload_send, file_upload_complete
# Property builders (clean payloads)
title_prop, rich_text_prop, select_prop, multi_select_prop
status_prop, number_prop, checkbox_prop, date_prop, url_prop
relation_prop, people_prop, files_prop
# Block builders
paragraph_block, heading_block, bulleted_list_item, numbered_list_item
to_do_block, code_block, divider_block, callout_block, quote_block
# Text helpers
title_text, rich_text_text
# Custom exceptions
NotionAPIError
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.
- 9d ago First seen · 281 lines · 79 tokens per session scan A f4a5cb303d6f
notion-api is a skill published in the GitHub repository avizmarlon/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 2,406 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
notebooklm-manager
Manages NotebookLM notebooks — query, add, list, search, enable/disable, remove. Use when a notebooklm.google.com URL appears or user mentions NotebookLM. Handles URLs through its own Chrome agent — do not navigate directly. Requires: claude-in-chrome MCP.
lx
Codebase exploration tool that reads many files or whole directories in a single call, with per-file headers, glob include/exclude filters, function/type skeleton extraction (signatures only, no bodies), and head/tail line slicing.
find-plugin-file
This skill should be used when needing to locate files within the Claude Code plugins cache directory (/.claude/plugins/cache). Triggers include finding tool scripts, skill files, or any plugin resource when the hardcoded path is unknown or varies by plugin version. Use when slash commands or orchestrators need to…
flow-lean
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
morning-triage
Discovery for an autonomous loop — find this turn's work instead of being handed it. Reads what changed since the last run (failed CI, new issues, merged commits), judges what's actually worth acting on, writes findings to a durable state file, and hands each off to the SDLC loop with a stop-condition. Use as the…
eco-max
Maximum-savings variant of /eco - the same frugality rules PLUS a low reasoning-effort override for the invoked task. Use for routine chores (rename, small fix, quick question, boilerplate) when the user wants absolute minimum token spend; prefer plain /eco for hard or high-stakes work. Works in any language.