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 ManceRayder42/jarvis-os --skill research-notebookgit clone --depth 1 https://github.com/ManceRayder42/jarvis-osWrote 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/mancerayder42/jarvis-os/research-notebook)<a href="https://agentmods.dev/skills/mancerayder42/jarvis-os/research-notebook"><img src="https://agentmods.dev/badge/skills/mancerayder42/jarvis-os/research-notebook/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/mancerayder42/jarvis-os/research-notebook"><img src="https://agentmods.dev/badge/skills/mancerayder42/jarvis-os/research-notebook.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00130 | $0.01424 |
| Opus 5 | $0.00065 | $0.00712 |
| Sonnet 5 | $0.00026 | $0.00285 |
| Haiku 4.5 | $0.00013 | $0.00142 |
Grade A, and why
research-notebook 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
research-notebook — NotebookLM-Powered Research Skill
Routes any research request through the user's local notebooklm CLI so collected sources, summaries, and Q&A become a durable, queryable artifact rather than scrollback.
Prerequisite
This skill assumes the notebooklm CLI is installed and authenticated (Google account) separately — it is not bundled with this plugin. If notebooklm list fails outright, tell the user it needs installing/logging in rather than silently falling back to plain web search.
When to use
- User asks to research, investigate, or dig into a topic (any language).
- User compares options, evaluates a tool, asks "what's the best way to do X", or wants a strategic overview.
- Single-shot factual lookups that would benefit from cited sources (e.g. "find out about Vercel Edge limits in 2026").
When NOT to use
- Trivial single-fact answers the model already knows confidently and the user just wants in chat.
- Questions about the user's own hub/notes — that's the
qmdskill, if installed. - An already-existing project-specific research workflow the user has of their own.
- Pure code questions answerable by reading the repo.
Workflow
Step 1 — Extract the topic
Pull 1–5 keywords from the user message. If the topic is unclear or too broad to act on, ask ONE clarifying question before continuing. Preserve the user's language.
Step 2 — Check for an existing notebook FIRST
notebooklm list
Fuzzy-match the topic against existing titles. If a clear match exists, reuse it:
notebooklm use <partial-id>
Otherwise create a new notebook with a Title Case + descriptive name including the year:
notebooklm create "Vercel Edge Functions Best Practices 2026"
Capture the new ID from output. Never duplicate an obviously-overlapping notebook.
Step 3 — Decide scope: small vs large
| Scope | Heuristic | Action |
|---|---|---|
| Small | Single specific question, named tool/concept, "what is X", quick lookup | NotebookLM only |
| Large | Multi-faceted topic, "best way to do Y", N-way comparison, strategic question | NotebookLM + signal main thread to fan out |
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 · 112 lines · 130 tokens per session scan A 0b99c7523643
research-notebook is a skill published in the GitHub repository ManceRayder42/jarvis-os (5 stars, last pushed 5d ago), licensed MIT. It adds 130 tokens to every session and 1,424 once invoked, about $0.0006 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 skills, from other repositories
confidence-gate
When you're about to claim success ("fixed", "done", "works", "passing tests") at the end of a turn, verify the claim is backed by actual evidence in this session. presence's Stop hook will flag a success claim that has no recent test/build pass behind it. Be aware of this gate and either run the verification, or…
evolve-lite:save-trajectory
Save the current conversation as a trajectory JSON file in OpenAI chat completion format for analysis and fine-tuning.
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
test-run
Run plugin test suites in this monorepo and report a concise pass/fail summary. Optional plugin slug arg; without arg, runs all plugins under plugins/.
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
graphify
Use when the user invokes /graphify or asks to build, update, or query a knowledge graph from a folder of files (code, docs, papers, notes, images). Triggers: 'map this codebase', 'graph my notes', 'what is connected across these files', 'community detection', 'GraphRAG', incremental graph update, Neo4j/SVG/GraphML…