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/teacherop/noobbook/claude-mdgit clone --depth 1 https://github.com/TeacherOp/NoobBookWrote 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/teacherop/noobbook/claude-md)<a href="https://agentmods.dev/instructions/teacherop/noobbook/claude-md"><img src="https://agentmods.dev/badge/instructions/teacherop/noobbook/claude-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 | $0.05267 | $0.05267 |
| Opus 5 | $0.02634 | $0.02634 |
| Sonnet 5 | $0.01053 | $0.01053 |
| Haiku 4.5 | $0.00527 | $0.00527 |
Grade A, and why
NoobBook CLAUDE.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 — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code (claude.ai/code) working in this repository. Keep this file lean — it's loaded into every session's context window. Deep details belong in code comments next to the thing they document.
What NoobBook is
Open-source NotebookLM alternative. React frontend + Flask backend, self-hosted Supabase for data + storage + auth. Website: noobbooklm.com.
Two views, that's it:
- Dashboard — project list (create / open / delete) + course resources.
- Project Workspace — three panels: Sources (multi-modal ingestion) · Chat (RAG Q&A with citations + voice) · Studio (content generation — fully built, not "planned").
Run / build
bin/setup # First-time: venv + deps for backend & frontend
bin/dev # Start both servers (backend :5001, vite :5173)
bin/dev --backend-only
bin/dev --frontend-only
bin/dev --install # Refresh deps before starting
cd frontend && npm run build # Production frontend build
cd frontend && npm run lint # ESLint
cd backend && pytest # Backend tests (372+ currently)
System deps: libreoffice and ffmpeg (audio + DOCX/PPTX paths). On macOS: brew install libreoffice ffmpeg.
Docker / self-hosted Supabase: see docker/MAC_SETUP.md. 16 containers (Supabase stack + backend + frontend + migrate).
Production: Coolify behind Traefik on a bare-metal IOFlood box. The production compose file is docker-compose-dev.yml (NOT docker-compose.yml, which is the local-dev stack).
Env vars
Create backend/.env. Minimum:
# Required
ANTHROPIC_API_KEY=sk-ant-...
OPENAI_API_KEY=sk-...
PINECONE_API_KEY=...
PINECONE_INDEX_NAME=...
# Supabase
SUPABASE_URL=http://kong:8000 # internal Docker hostname in prod
SUPABASE_PUBLIC_URL=https://<your-host> # browser-reachable host — REQUIRED in prod
# so signed storage URLs work
SUPABASE_ANON_KEY=...
SUPABASE_SERVICE_KEY=...
JWT_SECRET=... # needed for signature-verified fail-open
# Per-feature (optional)
ELEVENLABS_API_KEY=... # Audio / voice transcription
TAVILY_API_KEY=... # Web search fallback
GOOGLE_CLIENT_ID=... # Google Drive import (+ SECRET)
NOTION_API_KEY=...
FRESHDESK_API_KEY=... # + FRESHDESK_DOMAIN
JIRA_CLOUD_ID=... # + JIRA_EMAIL, JIRA_API_KEY
MIXPANEL_SERVICE_ACCOUNT_USERNAME=... # + SECRET + PROJECT_ID + REGION (us|eu|in)
ANTHROPIC_TIER=1 # 1-4, controls worker count + rate limits
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 · 412 lines · 5,267 tokens per session scan A 77e10829e863
NoobBook CLAUDE.md is an instructions file published in the GitHub repository TeacherOp/NoobBook (20 stars, last pushed 3mo ago), licensed MIT. It adds 5,267 tokens to every session, about $0.0263 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.