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/ed-donner/tech2ai/agents-mdgit clone --depth 1 https://github.com/ed-donner/tech2aiWhat 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 | $0.02011 | $0.02011 |
| Opus 5 | $0.01006 | $0.01006 |
| Sonnet 5 | $0.00402 | $0.00402 |
| Haiku 4.5 | $0.00201 | $0.00201 |
Grade A, and why
tech2ai 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
From Software Engineer to AI Data Scientist
Introduction
Context
This repo accompanies an online Live Event hosted by Ed Donner. Ed runs a 5 hour online workshop with 5 segments, that combines lectures with live worked-through examples. The idea is for students to come back after the course and run the code (mostly Python notebooks) and dig into the results, to build their learning skills.
Your role as Coding Agent
You should help the student to understand the material in these exercises, answer their questions, troubleshoot any problems, and give them more background information as relevant.
The topic of the Live Event
The Live Event is called "From Software Engineer to AI Data Scientist". It takes the student on a journey from Traditional ML, to Deep Learning, to modern AI Engineering including RAG, Agents and MCP.
Environment setup
We use the popular, fast package manager uv to set up a Python 3.12 environment. Instructions are in the README.md and in setup/SETUP-new.md
If the student has problems with setup, please read the setup instructions carefully and help them to troubleshoot. Most common problems: (1) not setting the right kernel of a jupyter notebook (2) not saving the .env file after entering a key.
Additional materials
The guides/ folder contains a number of reference guides with more background information for the student.
Ed is always available at [email protected] and happy to answer questions! And he's very responsive, typically replying within hours.
The segments
The main directories of the repo contain the code and exercises for each segment of the live event
Segment 1: Teaser
Before we go deeply into Traditional ML, we start with a whirlwind tour of AI Engineering. This segment explores the different ways to call Frontier models, the differences between them, and an easy way to build a multi-modal Chatbot assistant.
segment1/lab1.ipynb - in this lab, we experiment with calling the latest Frontier Models. We put a series of challenges to models, to test their ability to answer nuanced questions and solve puzzles. We compare training time scaling with inference time (reasoning). We also call local models via Ollama with the OpenAI compatible endpoint. We end with an entertaining dialog between LLMs.
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 · 105 lines · 2,011 tokens per session scan A e91c6c87b6cc
tech2ai AGENTS.md is an instructions file published in the GitHub repository ed-donner/tech2ai (256 stars, last pushed 3mo ago), licensed MIT. It adds 2,011 tokens to every session, about $0.0101 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
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.
designing-real-world-ai-agents-workshop CLAUDE.md
Instructions for iusztinpaul/designing-real-world-ai-agents-workshop, covering project, project structure, tech stack, access documentation and running qa.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
canvas-lms-mcp AGENTS.md
Instructions for bruchris/canvas-lms-mcp, covering agents.md — canvas lms mcp server, quick start, run with npx (no install needed), or install globally and architecture.
obsidian-university-workflow CLAUDE.md
Instructions for ABO896/obsidian-university-workflow, covering obsidian university workflow, project structure, rules for working on this project, templater api — always read the docs first and config alignment.
paper-pilot CLAUDE.md
Instructions for aytzey/paper-pilot, covering claude.md, best fit, setup, first workflow to try and claude prompt patterns.