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 agentmods add rules/ibaifernandez/notebooklm-skill/wrapupgit clone --depth 1 https://github.com/ibaifernandez/notebooklm-skillWhat 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 | $0.00045 | $0.00433 |
| Opus 5 | $0.00023 | $0.00217 |
| Sonnet 5 | $0.00009 | $0.00087 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
wrapup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Session Wrap-Up
Runs at end of session to capture decisions, save context, and push a log to NotebookLM.
Step 1 — Find target notebook
Check for project notebook:
cat "$(pwd)/.notebooklm/config.json" 2>/dev/null
If found, use that notebook ID. Otherwise check ~/.notebooklm/registry.json
for the current path. If neither exists, ask the user to run @notebooklm init
first.
Step 2 — Review the session
Look back through the conversation and identify:
- Work completed — what was built, fixed, or configured
- Decisions made — what was decided and why
- Key learnings — non-obvious insights
- Open threads — unfinished items for next session
Step 3 — Write session log
Create a markdown file at .notebooklm/sessions/session-YYYY-MM-DD.md:
# Session Summary — YYYY-MM-DD
**Project:** <project name>
## What We Did
- ...
## Decisions Made
- ...
## Key Learnings
- ...
## Open Threads
- ...
## Tools & Systems Touched
- ...
Step 4 — Push to NotebookLM
NOTEBOOK_ID=$(python3 -c "import json,pathlib; print(json.loads(pathlib.Path('.notebooklm/config.json').read_text())['notebook_id'])")
notebooklm source add .notebooklm/sessions/session-YYYY-MM-DD.md --notebook "$NOTEBOOK_ID"
Step 5 — Confirm
Tell the user: what was captured, where it was saved, and any open threads to pick up next time. One short paragraph.
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.
- 2d ago First seen · 81 lines · 45 tokens per session scan A ba952ecf754b
wrapup is a cursor rule published in the GitHub repository ibaifernandez/notebooklm-skill (5 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 433 once invoked, about $0.0002 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 2026-08-31.
Other cursor rules, from other repositories
documentation-standards
WHEN creating or modifying documentation files ENSURE consistent formatting and organization standards.
archive
Cursor rule "archive" from savagelysubtle/BIG-BRAIN-Memory-Bank, covering task archiving protocol, 📁 archive setup, 📋 archive format, task: [task name] (v1.0) and implementation results.
reflection-format
Reflection format and requirements.
200-quality-verification-procedures
description: WHEN verifying design quality APPLY systematic procedures for validation globs: ["/.md", "/.mdc"] alwaysApply: true.
210-artifact-management-system
description: WHEN managing design artifacts APPLY structured processes for organization and preservation globs: ["/.md", "/.mdc"] alwaysApply: true.
160-workflow-orchestration
WHEN executing tasks MANAGE workflow processes for consistent memory operations.