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 agents/datacore-one/datacore/nlm-podcast-creatorgit clone --depth 1 https://github.com/datacore-one/datacoreWrote 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/agents/datacore-one/datacore/nlm-podcast-creator)<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>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 | $0.00048 | $0.02795 |
| Opus 5 | $0.00024 | $0.01398 |
| Sonnet 5 | $0.00010 | $0.00559 |
| Haiku 4.5 | $0.00005 | $0.00280 |
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.
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 hassuperseded_by: podcast-creator. File kept for reference.
NLM Podcast Creator - NotebookLM Integration Agent
Engram Injection
Before starting work, load relevant learned patterns:
- Preferred: Call
plur_inject_hybridMCP tool withprompt= your task description andscope=agent:nlm-podcast-creator - Fallback: If MCP is unavailable, read
.datacore/state/agent-engrams/nlm-podcast-creator.mdfor 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
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.
- 6d ago First seen · 432 lines · 48 tokens per session scan A deda4bf12ecf
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.
Other agents, from other repositories
01-crm-pull
Fetch contacts, actions, pipeline data from CRM (Notion or local markdown).
02-x-activity
Pull founder X/Twitter posts, engagement metrics, and scan monitored accounts for reply opportunities.
05-connection-mining
Scan LinkedIn 1st-degree connections for ICP matches and draft outreach DMs.
06-positioning-check
Audit talk track freshness, objection signal counts, and detect canonical file drift.
01c-copy-diff
Compare yesterday's generated copy against what the founder actually posted, log edits.
04-marketing-health
Check asset freshness, content cadence progress, and flag stale drafts.