Borrowing it
Nothing to install: this file belongs to LinZhuoChen/video-to-notebook. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/LinZhuoChen/video-to-notebook/main/AGENTS.mdgit clone --depth 1 https://github.com/LinZhuoChen/video-to-notebookWrote 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/linzhuochen/video-to-notebook/agents-md)<a href="https://agentmods.dev/instructions/linzhuochen/video-to-notebook/agents-md"><img src="https://agentmods.dev/badge/instructions/linzhuochen/video-to-notebook/agents-md/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/instructions/linzhuochen/video-to-notebook/agents-md"><img src="https://agentmods.dev/badge/instructions/linzhuochen/video-to-notebook/agents-md.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 | $0.03394 | $0.03394 |
| Opus 5.5 | $0.01358 | $0.01358 |
| Sonnet 5.5 | $0.00679 | $0.00679 |
| Haiku 4.5 | $0.00339 | $0.00339 |
Grade C, and why
video-to-notebook AGENTS.md scanned grade C with 1 finding 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 2mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .video-to-notebook/textbook/*.html .video-to-notebook/concepts/*.html How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents guide
This file orients AI coding agents (OpenAI Codex CLI, Cursor, Continue, Aider, …) to the video-to-notebook codebase. Claude Code users: see
skills/video-to-notebook/SKILL.mdfor the equivalent skill-format walkthrough — the two files cover the same ground.
What this repo is
A Python CLI + Astro static-site generator that:
- Crawls YouTube + Bilibili playlists with
yt-dlp→ SQLite. - Tags transcript chunks with concept labels via Claude (or any agent).
- Clusters proposed tags into a unified ontology.
- Synthesizes a beginner-friendly textbook (one HTML chapter per concept group).
- Explains each concept as a rich illustrated encyclopedia entry.
- Builds the lot into a static Astro site you can host on GitHub Pages.
Agent-driven workflow (default in v2.3+)
Every LLM stage (tag, cluster, curriculum, synthesize, explain) runs in-session by default — no ANTHROPIC_API_KEY required. The CLI writes a JSON prompts envelope to <state_dir>/prompts/<step>.json and exits. You read the envelope, reason, write a decisions JSON to the sibling .decisions.json path, then re-invoke the same command with --apply. The CLI applies your decisions to SQLite.
tag and cluster also expose an opt-in --use-api flag that drives the Anthropic SDK directly (if you have a key). curriculum, synthesize, explain are in-session-only — they have no API path.
The protocol is agent-agnostic. Schemas, conventions, idempotency guarantees, error semantics all live in docs/AGENT_PROTOCOL.md. Read that file before driving the pipeline for the first time.
Quick start for Codex / any agent
mkdir my-study-site && cd my-study-site
video-to-notebook init
video-to-notebook crawl "<youtube-or-bilibili-url>" --name <slug>
# Repeat crawl for each course
# Then, for each LLM stage:
video-to-notebook <stage> [args]
# CLI writes <state_dir>/prompts/<step>.json and prints a 3-line stderr hint.
# You read the envelope, reason, write <state_dir>/prompts/<step>.decisions.json.
video-to-notebook <stage> [args] --apply
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.
- 2mo ago First seen · 219 lines · 3,394 tokens per session scan C f960b2b51152
video-to-notebook AGENTS.md is an instructions file published in the GitHub repository LinZhuoChen/video-to-notebook (22 stars, last pushed 5mo ago), licensed MIT. It adds 3,394 tokens to every session, about $0.0136 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
video-to-notebook AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| video-to-notebook AGENTS.mdLinZhuoChen/video-to-notebook | Instructions file | 22 | 5mo ago | MIT | C | 3,394 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |