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 lox/notion-cli --skill notiongit clone --depth 1 https://github.com/lox/notion-cliWrote 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/lox/notion-cli/notion)<a href="https://agentmods.dev/skills/lox/notion-cli/notion"><img src="https://agentmods.dev/badge/skills/lox/notion-cli/notion/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/lox/notion-cli/notion"><img src="https://agentmods.dev/badge/skills/lox/notion-cli/notion.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 72 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
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 | $0.00032 | $0.02172 |
| Opus 5.5 | $0.00013 | $0.00869 |
| Sonnet 5.5 | $0.00006 | $0.00434 |
| Haiku 4.5 | $0.00003 | $0.00217 |
Grade A, and why
notion 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 2mo 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.
Notion CLI
A CLI to manage Notion from the command line, using Notion's remote MCP server.
Prerequisites
The notion-cli command must be available on PATH. To check:
notion-cli version
If not installed:
go install github.com/lox/notion-cli@latest
Or see: https://github.com/lox/notion-cli
Authentication
The CLI uses OAuth authentication for MCP-backed commands. On first use, it opens a browser for authorization:
notion-cli auth login # Authenticate with Notion
notion-cli auth status # Show active profile and OAuth state (diagnostic)
notion-cli auth refresh # Force-refresh; commands auto-refresh on use, so rarely needed
notion-cli auth logout # Clear credentials
For CI/headless environments, set NOTION_ACCESS_TOKEN environment variable.
Some fallback features also use the official Notion API:
notion-cli auth api setup
notion-cli auth api status
notion-cli auth api verify
notion-cli auth api unset
For CI/headless environments, set NOTION_API_TOKEN.
Multiple accounts
Every command accepts --profile <name> (or NOTION_CLI_PROFILE) to target a specific Notion account. Named profiles keep credentials isolated under ~/.config/notion-cli/profiles/<profile>/; the implicit default profile uses the existing top-level paths.
notion-cli auth login --profile work
notion-cli page list --profile work
export NOTION_CLI_PROFILE=work # pin for the shell session
notion-cli auth use work # make work the default profile
Resolution precedence: --profile > NOTION_CLI_PROFILE > notion-cli auth use <name> > implicit default profile.
Available Commands
notion-cli auth # Manage authentication
notion-cli page # Manage pages (list, view, create, upload, edit)
notion-cli db # Manage databases (list, query, create entries)
notion-cli search # Search the workspace
notion-cli comment # Manage comments (list, create)
notion-cli tools # List available MCP tools
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.
- 2mo ago First seen · 210 lines · 32 tokens per session scan A 0699042ef843
notion is a skill published in the GitHub repository lox/notion-cli (37 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 2,172 once invoked, about $0.0001 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…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.