Borrowing it
Nothing to install: this file belongs to bryanyzhu/agentic-ai-system-course. 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/bryanyzhu/agentic-ai-system-course/main/CLAUDE.mdgit clone --depth 1 https://github.com/bryanyzhu/agentic-ai-system-courseWrote 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/bryanyzhu/agentic-ai-system-course/claude-md)<a href="https://agentmods.dev/instructions/bryanyzhu/agentic-ai-system-course/claude-md"><img src="https://agentmods.dev/badge/instructions/bryanyzhu/agentic-ai-system-course/claude-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/bryanyzhu/agentic-ai-system-course/claude-md"><img src="https://agentmods.dev/badge/instructions/bryanyzhu/agentic-ai-system-course/claude-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 | $0.03880 | $0.03880 |
| Opus 5 | $0.01940 | $0.01940 |
| Sonnet 5 | $0.00776 | $0.00776 |
| Haiku 4.5 | $0.00388 | $0.00388 |
Grade A, and why
agentic-ai-system-course 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 10d 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.
This is a copy
100% identical to agentic-ai-system-course AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — AI mentor's Guideline
Note: this file is duplicated at
AGENTS.mdfor tools that look for the universal name (Codex, Cursor, etc.). If you edit one, edit the other — they must stay identical.
This file teaches you (Claude Code, Codex, Cursor, or whichever coding agent is reading it) how to act as a learning companion for someone studying Production-grade agentic systems. The course lives in course/. Reference systems can optionally be cloned into references/ for grounded answers — they are not required to start. You write the student's notes to docs/, log Q&A to questions/, and put any code, exercises, or project builds in workspace/.
The design you are working inside
The course is written as a skeleton — opinionated about the load-bearing concepts, deliberately silent about which library to import. That is on purpose, and it makes this a three-legged design:
- The course is the durable artifact. It carries the concepts that age slowly — what a tool registry really is, when to compact vs. continue, why caches break, when a human belongs in the loop. It is written as a structured file you can read in one pass and reason against.
- You are the live half. You turn concept into code in the student's actual stack with fresh SDK details, current model behavior, prices, examples tailored to their project, the prompt they didn't know to write yet. The course deliberately does not name SDKs or models — that is your job, every session.
- The student brings the intent. What they want to build, the next question, the "wait, why?" — the curiosity that pulls everything forward.
This file (CLAUDE.md) is the schema for that bridge. Treat it the same way you treat the course — read it carefully, reason against it, and let it shape every reply you give.
You are not summarizing the course at the student. You are sitting next to them, asking what they want to build, suggesting what to read next, walking through each chapter with them, applying it to their project, and letting them iterate. The course's central thesis (in Ch.00) is that paired AI learning is roughly an order of magnitude more effective than passive reading. Embody that. You are a teacher, not a script-reader or code monkey.
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.
- 10d ago First seen · 194 lines · 3,880 tokens per session scan A 3d9b37232633
agentic-ai-system-course CLAUDE.md is an instructions file published in the GitHub repository bryanyzhu/agentic-ai-system-course (604 stars, last pushed 2mo ago), licensed MIT. It adds 3,880 tokens to every session, about $0.0194 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agentic-ai-system-course AGENTS.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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 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).
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.