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/robiton/notebooklm-mcp-cli/agents-mdgit clone --depth 1 https://github.com/Robiton/notebooklm-mcp-cliWhat 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 | $0.00278 | $0.00278 |
| Opus 5 | $0.00139 | $0.00139 |
| Sonnet 5 | $0.00056 | $0.00056 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
notebooklm-mcp-cli 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 2d 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.
What it actually says
AI Context Bootstrap
Read ai/STANDARDS.md and load all files in the order it specifies
before beginning any work. Do not start coding, planning, or responding
until the full load order is complete.
This project uses version format: MAJOR.MINOR.PATCH.YYYYMMDD.HHMM Example: 1.0.0.20260325.0624
At the end of every session, update ai/SESSION.md and ai/BACKLOG.md.
Never store credentials, secrets, or PHI in any ai/ file.
End of session — required before closing
Before ending any session, you MUST:
- Update
ai/SESSION.md— what was done, decisions made, next steps - Update
ai/BACKLOG.md— mark completed tasks, add new ones - Remind the user to commit and push both files
Supported tools
This file (AGENTS.md) is the universal standard read by all AI coding tools: Cursor, Codex, Windsurf, GitHub Copilot, Aider, Zed, Warp, Devin, and others.
CLAUDE.md is a symlink to this file for Claude Code compatibility.
If CLAUDE.md does not exist, run: ln -s AGENTS.md CLAUDE.md
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.
- 2d ago First seen · 29 lines · 278 tokens per session scan A 1dae8734b836
notebooklm-mcp-cli AGENTS.md is an instructions file published in the GitHub repository Robiton/notebooklm-mcp-cli (0 stars, last pushed 4mo ago), licensed MIT. It adds 278 tokens to every session, about $0.0014 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other instructions, from other repositories
markitdown-mcp AGENTS.md
Instructions for trsdn/markitdown-mcp, covering ai agents integration guide, 🤖 quick reference for ai agents, primary use cases, available tools and 🛠️ tool usage guide.
che-word-mcp CLAUDE.md
Claude Code instructions for PsychQuant/che-word-mcp, covering che-word-mcp 開發指引, 專案結構, 重要路徑規則, binary 安裝位置 and mcpb 打包檔位置.
tmdb-mcp AGENTS.md
Instructions for Grinv/tmdb-mcp, covering agents.md, project shape, commands, conventions and testing the live/published server.
steam-games-mcp AGENTS.md
Instructions for Grinv/steam-games-mcp, covering agents.md, project shape, commands, conventions and testing the live/published server.
mal-mcp AGENTS.md
Instructions for Grinv/mal-mcp, covering agents.md, project shape, commands, conventions and testing the live/published server.
FusionAL CLAUDE.md
Claude Code instructions for JRM-FusionAL/FusionAL, covering claude.md — fusional, session init — run this first, recall protocol (mandatory, visible), auto-log protocol (mandatory, ambient) and critical failure modes (already logged — do not repeat).