agentmods.dev

automated-notebooklm: Instructions file for Codex

AGENTS.md

automated-notebooklm AGENTS.md is an instructions file for Codex, OpenCode from omril321/automated-notebooklm. It costs 1,336 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for a TypeScript pipeline that turns articles from a Monday.com board into podcast episodes using Google NotebookLM and uploads them to RedCircle.

In plain words
What is it for?
Use it when changing or checking the podcast pipeline, including its tests, type checks, build, formatting, authentication setup, and podcast-generation command.
Why use it?
It explains the project layout, required tools, checks, and a live command that can use a daily quota, publish episodes, and edit board items. This helps prevent accidental real-world changes while working on the code.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is omril321/automated-notebooklm's own configuration. It tells Codex and OpenCode how to work on automated-notebooklm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything automated-notebooklm configures →

not rated 14repo yesterday A scan 1,336 tokens original Apache-2.0
View source ↗ omril321/automated-notebooklm
Reuse

Borrowing it

Nothing to install: this file belongs to omril321/automated-notebooklm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/omril321/automated-notebooklm/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/omril321/automated-notebooklm

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for automated-notebooklm AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/omril321/automated-notebooklm/agents-md/github.svg)](https://agentmods.dev/instructions/omril321/automated-notebooklm/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/omril321/automated-notebooklm/agents-md"><img src="https://agentmods.dev/badge/instructions/omril321/automated-notebooklm/agents-md/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.

agentmods 80×15 button for automated-notebooklm AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/omril321/automated-notebooklm/agents-md"><img src="https://agentmods.dev/badge/instructions/omril321/automated-notebooklm/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,336 This file is loaded in full into every session.
When invoked 1,336 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01336 $0.01336
Opus 5.5 $0.00534 $0.00534
Sonnet 5.5 $0.00267 $0.00267
Haiku 4.5 $0.00134 $0.00134

Measured yesterday against content hash 90ebc5583e5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

automated-notebooklm AGENTS.md 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 yesterday.

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.

AGENTS.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automated NotebookLM

TypeScript pipeline that turns articles curated on a Monday.com board into podcast episodes: it generates audio with Google NotebookLM (via the notebooklm-py CLI), uploads the MP3 to RedCircle (Playwright), and writes the result back to the board.

⚠️ yarn generate-podcasts is live

It spends NotebookLM's daily quota, publishes real RedCircle episodes, and edits Monday items. Never run it unless the user asks. Use yarn test:run, yarn typecheck and yarn build to verify changes.

Commands

yarn install
yarn test:run          # vitest, single run (yarn test = watch)
yarn typecheck         # tsc --noEmit
yarn build             # tsc -> dist/
yarn format            # prettier --write . (format:check to verify)
yarn generate-podcasts # the only entry point; see warning above

./scripts/setup-nlm.sh # one-time: .venv + notebooklm-py via uv (Python 3.10+)
./scripts/nlm login    # Google OAuth in a browser
./scripts/nlm list     # verify auth

Requires Node >= 24.4 (.nvmrc), yarn, uv, Chrome (RedCircle upload uses Playwright's chrome channel).

How a run works

Entry: src/scripts/generatePodcastForUrl.ts -> generateAndUploadFromMondayBoardCandidates() in src/mondayBatchOrchestrator.ts. No flags, no single-URL mode.

  1. Board prep (src/monday/service.ts): items whose name is a bare URL get title + link filled in; article items missing metadata get Type / Metadata / Non-podcastable set. URLs are processed 10 at a time with 15s pauses.
  2. Candidates: getPodcastCandidates(3) keeps items with podcastFitness > 0 and an http URL, sorts audio-ready items (see below) first, then by fitness desc, and takes the top 3.
  3. Generate: items with an existing NotebookLM link ("audio-ready") reuse that notebook and skip the rate limit; the rest are capped by remaining quota (audioGenerationTrackingService). Done through services/notebookLMAdapter.ts -> services/notebookLMCliService.ts.
  4. Upload: all MP3s go to RedCircle in one browser session (redCircleService.ts, browserService.ts).
  5. Write back: podcast link, NotebookLM link and item name are updated on Monday.

Read the full file on GitHub · 80 lines

Changes

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.

  1. yesterday First seen · 80 lines · 1,336 tokens per session scan A 90ebc5583e5f

Subscribe to this mod's changes

automated-notebooklm AGENTS.md is an instructions file published in the GitHub repository omril321/automated-notebooklm (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,336 tokens to every session, about $0.0053 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 2026-11-07.

Project management
Related

automated-notebooklm AGENTS.md compared with instructions from other repositories

automated-notebooklm AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
automated-notebooklm AGENTS.mdomril321/automated-notebooklmInstructions file14yesterdayApache-2.0A1,336Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot