Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ahkedia/lyra-ainpx agentmods add skills/ahkedia/lyra-ai/notionWrote 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/ahkedia/lyra-ai/notion)<a href="https://agentmods.dev/skills/ahkedia/lyra-ai/notion"><img src="https://agentmods.dev/badge/skills/ahkedia/lyra-ai/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/ahkedia/lyra-ai/notion"><img src="https://agentmods.dev/badge/skills/ahkedia/lyra-ai/notion.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 | $0.00017 | $0.02095 |
| Opus 5 | $0.00009 | $0.01047 |
| Sonnet 5 | $0.00003 | $0.00419 |
| Haiku 4.5 | $0.00002 | $0.00210 |
Grade A, and why
notion 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 10d 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.
**NEVER write directly to these databases via curl. Always use the Python CLI:** How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
notion
Use the Notion API to create/read/update pages, data sources (databases), and blocks.
⛔ HARD RULE — Reminders DBs MUST go through crud/cli.py
NEVER write directly to these databases via curl. Always use the Python CLI:
| DB name | database_id |
|---|---|
| Reminders - Akash | 32678008-9100-802f-ad9f-fb48ff5f4c1d |
| Reminders - Shared | 2054e39c-3f09-431d-8821-0e6a7513913a |
| Reminders - Abhigna | 5d6732b1-7e30-4856-b56b-edbf9c3df229 |
Use this command for ANY reminder write (eval, user, cron — all of them):
python3 /root/lyra-ai/crud/cli.py parse '<the user\'s reminder request verbatim>'
⛔ Write confirmation is MANDATORY:
After running crud/cli.py, the CLI prints a success line including the Notion page URL and/or page ID.
- ✅ CORRECT: Include the CLI output in your reply. Example: "Done — Reminder created."
- ❌ WRONG: Saying "Done." / "Reminder created." / "Added." without any CLI output — this means the write NEVER happened. Report failure instead.
- If the CLI produces no output or errors, the write failed. Say so explicitly.
Examples:
- User: "Add a reminder: call the dentist tomorrow at 3pm"
→
python3 /root/lyra-ai/crud/cli.py parse 'Add a reminder: call the dentist tomorrow at 3pm' - Cross-user: "create a shared reminder titled X"
→
NOTION_REMINDERS_DB_ID=2054e39c-3f09-431d-8821-0e6a7513913a python3 /root/lyra-ai/crud/cli.py parse 'Add a reminder: X'
Why this rule exists: the CLI auto-tags every page with a Source select property (user|eval|cron) based on the active session, which is what the eval cleanup pipeline relies on to keep test data out of prod. Writing directly via curl bypasses this and pollutes the production DBs.
If you genuinely cannot use the CLI (e.g., the schema needs a property the CLI doesn't set), include "Source": {"select": {"name": "user"}} (or "eval" / "cron") explicitly in your properties payload. The Source property is REQUIRED for Reminders DB writes.
What ships with it
2 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.
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.
- 10d ago First seen · 190 lines · 17 tokens per session scan A fc0fd25bdb0d
notion is a skill published in the GitHub repository ahkedia/lyra-ai (5 stars, last pushed 21d ago), licensed MIT. It adds 17 tokens to every session and 2,095 once invoked, about $0.0001 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
google-workspace
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
box
Box manages cloud files, sharing, search, and metadata.
ima-skill
A unified IMA skill for managing personal notes and knowledge bases through the platform's APIs.
notes
A note-management skill for searching, reading, creating, and adding content to personal notes in IMA, a note and knowledge platform.
apple-notes
Manage Apple Notes via the memo CLI on macOS (create, view, search, edit).
co-mail-and-drive
Read and send mail from the user's own Gmail or Outlook account, safely stage Gmail draft attachments, send from the agent's own address, manage Outlook contacts and the Outlook calendar, and work with Google Drive files — with co gmail, co outlook, co email, and co gdrive. Use when the user asks about their inbox, an…