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 instructions/prantikmedhi/lore/agents-mdgit clone --depth 1 https://github.com/prantikmedhi/loreWrote 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/instructions/prantikmedhi/lore/agents-md)<a href="https://agentmods.dev/instructions/prantikmedhi/lore/agents-md"><img src="https://agentmods.dev/badge/instructions/prantikmedhi/lore/agents-md.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 | $0.00479 | $0.00479 |
| Opus 5 | $0.00239 | $0.00239 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
lore 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 5d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lore Agent Guide
Target locale: en.
This repository provides a complete NotebookLM automation layer for AI assistants. Agents should use source-grounded workflows, preserve citations, and create requested artifacts with the local scripts.
Repository Surfaces
| Surface | Location | Purpose |
|---|---|---|
| CLI | scripts/ |
Notebook operations, pipeline planning, artifact builders. |
| MCP | mcp_server/ |
Tool helpers for MCP-compatible clients. |
| Skill | SKILL.md |
Agent behavior and workflow rules. |
| Docs | docs/ and references/ |
Setup, clients, API surface, output formats, recipes. |
Agent Rules
- Target locale:
en. - Do not add personal credits or attribution blocks.
- Prefer source-grounded NotebookLM answers.
- Preserve citations, URLs, titles, dates, and uncertainty.
- Use JSON plans when automation is needed.
- Use Markdown for human-facing reports.
- Create artifacts when user requests outputs, not only plans.
Powered Mode Workflow
- Classify sources with
lore-source-manifestorlore manifest. - Create or reuse notebook.
- Add all relevant sources.
- Ask focused research questions.
- Synthesize cited answer.
- Generate requested artifacts.
- Index outputs with
lore-export-bundle.
Common Commands
lore list
lore create --title "Research" --sources https://example.com
lore ask --notebook "Research" --query "What are the key findings?"
lore-pipeline generate-all --title "Research" --sources https://example.com --output output/plan.json
lore-report --input output/plan.json --output output/report.md
lore-ppt --input output/report.md --output output/deck.pptx
lore-study-pack --input output/report.md --output-dir output/study-pack
lore-export-bundle --artifact-dir output --output output/bundle.json
Expected Artifacts
- Structured research brief
- Cited answer
- Markdown report
- PPTX slide deck
- Podcast script
- Video plan
- Flashcards
- Quiz
- Mind map
- Architecture summary
- Code explanation
- Study pack
- Bundle index
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.
- 5d ago First seen · 64 lines · 479 tokens per session scan A eb0a0d385701
lore AGENTS.md is an instructions file published in the GitHub repository prantikmedhi/lore (2 stars, last pushed 1mo ago), licensed MIT. It adds 479 tokens to every session, about $0.0024 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 instructions, from other repositories
notebooklm-py CLAUDE.md
Claude Code instructions for teng-lin/notebooklm-py, covering claude.md, project overview, development commands, full guide: docs/installation.md and before pushing.
notebooklm-py AGENTS.md
AGENTS.md instructions for teng-lin/notebooklm-py, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
notebooklm-skill AGENTS.md
Instructions for claude-world/notebooklm-skill, covering notebooklm-skill, authentication, cli commands, notebooklm-skill — core operations and notebooklm-pipeline — workflow orchestration.
labrat AGENTS.md
Instructions for ProjectDXAI/labrat, covering labrat repo, source of truth, interface rules, frontier model rules and checks.
claude-world-studio CLAUDE.md
Instructions for claude-world/claude-world-studio, covering claude world studio, architecture, agentic subsystem (v2.2), db tables and key patterns.
airas copilot-instructions.md
Copilot instructions for airas-org/airas, a project described as: AIRAS - an open-source project for research automation.