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 skills add WenyuChiou/research-hub --skill notebooklm-brief-verifiergit clone --depth 1 https://github.com/WenyuChiou/research-hubWrote 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/wenyuchiou/research-hub/notebooklm-brief-verifier)<a href="https://agentmods.dev/skills/wenyuchiou/research-hub/notebooklm-brief-verifier"><img src="https://agentmods.dev/badge/skills/wenyuchiou/research-hub/notebooklm-brief-verifier/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/wenyuchiou/research-hub/notebooklm-brief-verifier"><img src="https://agentmods.dev/badge/skills/wenyuchiou/research-hub/notebooklm-brief-verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.01249 |
| Opus 5 | $0.00035 | $0.00624 |
| Sonnet 5 | $0.00014 | $0.00250 |
| Haiku 4.5 | $0.00007 | $0.00125 |
Grade A, and why
notebooklm-brief-verifier 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 11d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
notebooklm-brief-verifier
NotebookLM is great at producing readable briefs, but it can:
- Skip a source that was in the bundle (silently — no error).
- Make claims the source bundle doesn't actually support.
- Contradict claims across sources without flagging the conflict.
- Generalize beyond the data ("studies show...") when one paper says something narrow.
This skill verifies a downloaded brief against the actual source bundle that research-hub uploaded, so the user can trust (or distrust) the brief before sharing or citing.
When to use
Trigger phrases:
- "Check this NotebookLM brief against the source bundle."
- "Verify whether NotebookLM missed or hallucinated anything important."
- "Compare downloaded NotebookLM notes to the cluster papers."
- "Audit this brief before I send it to my advisor."
Not for:
- Generating the brief in the first place — that's
research-hub notebooklm generate. - Comparing papers to each other —
literature-triage-matrix. - Manuscript-level claim audit —
academic-writing-skills.
Inputs
In priority order:
-
research-hub-managed mode (default). When the brief was generated via
research-hub notebooklm generate+download:- Brief:
.research_hub/artifacts/<cluster>/brief-*.txt - Bundle manifest:
.research_hub/bundles/<cluster>/manifest.json— list of which source files were uploaded. - Cluster Obsidian notes under
raw/<cluster>/*.md— for spot-checking specific claims. - Source PDFs under
pdfs/<cluster>/— last-resort spot-check only; cap at 3 per session.
- Brief:
-
Manual fallback mode (new in v0.68.x). When the user generated the brief themselves on notebooklm.google.com — direct upload, web UI, copy-paste — research-hub never saw the bundle. Accept either CLI flags or a paste-into-chat:
--brief <path-to-brief.{md,txt,pdf}>— the downloaded brief file (any path, not just.research_hub/artifacts/).--sources <path-to-source-list.{yml,md,json}>— a plain list of the source titles + DOIs / URLs the user uploaded to NLM.
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.
- 11d ago First seen · 123 lines · 70 tokens per session scan A 80c71c94e3e5
notebooklm-brief-verifier is a skill published in the GitHub repository WenyuChiou/research-hub (54 stars, last pushed 3d ago), licensed MIT. It adds 70 tokens to every session and 1,249 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
migrate-v0-to-v1
Migrate a Scraps wiki from v0 to v1. Use this whenever the user asks to upgrade Scraps, migrate v0 wiki syntax/config, convert implicit tags to explicit #[[tag]], move from scraps-writer to scraps, or audit a wiki for v1 readiness. This skill is designed for one-pass LLM-led migrations that discover the latest v0 and…
remem
Use when the user asks Codex to recall prior project context, save durable decisions or bug fixes, inspect remem memory health, or activate remem automatic memory hooks from the Codex plugin.
ingest
Create a new scrap from a source (prompt, URL, or arbitrary markdown), update cross-links in related scraps, and run a sanity check. Use this when the user wants to add a scrap, summarize an article, save synthesized content to the wiki, or file back a Q&A result.
query
Answer questions about the wiki by searching, reading, and synthesizing relevant scraps with [[Title]] citations. Use this when the user wants to query the wiki, ask what they have written about a topic, compare scraps, find related notes, or pull a synthesized overview from existing scraps.
planning-with-scratchpad
Use when user explicitly requests planning with a scratchpad, or asks for persistent tracking of a complex task that the human can browse visually. Backs planning files with the scratch CLI so a pad's files are registered and viewable.
scratch
Organize knowledge from an agent session into a scratchpad — a folder of files plus a scratchpad.json manifest. Use when a task generates notes, snippets, command output, diagrams, or artifacts worth keeping together for a session/activity.