nlm-podcast-creator

nlm-podcast-creator is an agent for Claude Code from datacore-one/datacore. It costs 48 tokens per session (2,795 once invoked), scanned A, original, MIT.

A retired agent for creating NotebookLM podcasts from selected sources. NotebookLM is a tool that turns supplied research materials into summaries and audio overviews.

In plain words
What is it for?
Use it only as a reference for the former process of creating notebooks, adding URLs or files, generating audio overviews, and downloading the result.
Why use it?
It documents an older research workflow, but the entry says it has been replaced by another podcast-creator agent.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Install

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.

agentmods
npx agentmods add agents/datacore-one/datacore/nlm-podcast-creator
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore

Made for: Claude Code.

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 nlm-podcast-creator

README.md
[![agentmods](https://agentmods.dev/badge/agents/datacore-one/datacore/nlm-podcast-creator.svg)](https://agentmods.dev/agents/datacore-one/datacore/nlm-podcast-creator)
Your own site
<a href="https://agentmods.dev/agents/datacore-one/datacore/nlm-podcast-creator"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/nlm-podcast-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,795 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00048 $0.02795
Opus 5 $0.00024 $0.01398
Sonnet 5 $0.00010 $0.00559
Haiku 4.5 $0.00005 $0.00280

Measured 6d ago against content hash deda4bf12ecf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

nlm-podcast-creator 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 6d 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.

.datacore/4-archive/agents/nlm-podcast-creator.md · 432 lines

How it starts

The opening of the file, as written. The whole thing — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DEPRECATED per DIP-0021: Replaced by podcast-creator. Registry entry has superseded_by: podcast-creator. File kept for reference.

NLM Podcast Creator - NotebookLM Integration Agent

Engram Injection

Before starting work, load relevant learned patterns:

  1. Preferred: Call plur_inject_hybrid MCP tool with prompt = your task description and scope = agent:nlm-podcast-creator
  2. Fallback: If MCP is unavailable, read .datacore/state/agent-engrams/nlm-podcast-creator.md for compiled engrams

Engrams encode learned behavioral patterns that improve task quality.

Agent Context

Role in Research Pipeline

Generates high-quality NotebookLM podcasts from curated source lists, managing the full lifecycle from notebook creation to audio download.

Responsibilities:

  • Validate source count and quality (optimal: 5-10 sources per podcast)
  • Create or reuse NotebookLM notebooks with appropriate naming
  • Add URLs and local files as sources via nlm CLI
  • Generate audio overviews with custom instructions for depth and coherence
  • Monitor generation status and handle timeouts/failures
  • Download completed podcasts to designated output directory
  • Return structured results with file paths and metadata

Quick Reference

Question Answer
When am I invoked? By daily-research-processor for daily/topical podcasts, or by /create-podcast for ad-hoc requests
What's the optimal source count? 5-10 sources for deep coverage (min 3, max 12)
How long does generation take? Typically 5-10 minutes, timeout at 30 minutes
What's the target duration? 30 minutes for comprehensive coverage
Where are podcasts saved? 0-personal/content/podcasts/ or team space content/podcasts/

Integration Points

  • daily-research-processor - Invokes for overnight podcast generation (daily news + topical)
  • /create-podcast command - Invokes for user-requested ad-hoc podcasts
  • nlm CLI - External tool for NotebookLM notebook and audio management
  • Podcast output directory - Files saved to 0-personal/content/podcasts/
  • Morning briefing - Podcast links included in daily research briefing

Read the full file on GitHub · 432 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. 6d ago First seen · 432 lines · 48 tokens per session scan A deda4bf12ecf

Subscribe to this mod's changes

nlm-podcast-creator is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 2,795 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.