ab100 CLAUDE.md

ab100 CLAUDE.md is an instructions file for coding agents from timothywarner-org/ab100. It costs 3,925 tokens per session, scanned A, original, MIT.

A project instruction file for a repository that contains Microsoft AB-100 training material, a study agent and a small Azure deployment example using an AI agent and MCP.

In plain words
What is it for?
Use it to guide work on the course materials, certification practice agent, deployment scripts, MCP server and related Azure infrastructure.
Why use it?
It explains the repository’s purpose and major parts so a coding agent can make changes in the right area.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/timothywarner-org/ab100/claude-md
Clone the repo
git clone --depth 1 https://github.com/timothywarner-org/ab100

Wrote 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.

agentmods badge for ab100 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/timothywarner-org/ab100/claude-md.svg)](https://agentmods.dev/instructions/timothywarner-org/ab100/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/timothywarner-org/ab100/claude-md"><img src="https://agentmods.dev/badge/instructions/timothywarner-org/ab100/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,925 This file is loaded in full into every session.
When invoked 3,925 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03925 $0.03925
Opus 5 $0.01962 $0.01962
Sonnet 5 $0.00785 $0.00785
Haiku 4.5 $0.00392 $0.00392

Measured 5d ago against content hash aca23eee2ab9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ab100 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.

CLAUDE.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Repository purpose

This repo has three complementary missions:

  1. Live training scaffolding -- companion material for Tim Warner's O'Reilly Live Learning course Agentic AI Business Solutions Architect (4 hours, delivered April 2026). The authoritative plan is docs/course-plan-april-2026.md.
  2. AB-100 Cert Buddy -- a GitHub Copilot agent that generates practice questions, hands-on labs, and personalized study plans for Microsoft exam AB-100: Agentic AI Business Solutions Architect. The agent, skills, prompts, and MCP server live under .github/ and .vscode/.
  3. Hour 3 Deploy POC stack -- a working Foundry agent + MCP + ACA + APIM proof of concept under src/. Five bash scripts spin up the gateway-fronted MCP server that wraps an existing Foundry agent; one script tears it down. Used as the live demo for Hour 3 (Deploy) and as the structural base for the Hour 4 (Security) bridge.

This is Tim Warner's instructor source of truth and learner reference material. There is one minimal Python app (the MCP server in src/app/) and one Bicep stack; no test suite. Build pipelines: the slide deck (see "Slide deck build" below) and the POC deploy scripts (see "POC stack" below).

Slide deck build

The course slide deck is generated from HTML source files via Node, not authored in PowerPoint:

  • Source: docs/deck-build/slides/*.html -- one HTML file per slide, ordered by filename. Slides use Tim's brand palette (#1F2A56 navy, #00B4D8 cyan, #F4845F orange) and a fixed 720pt x 405pt 16:9 layout. Existing CSS classes (.header, .tag, .box, .card, .foot) define the look -- match them when adding slides.
  • Build: cd docs/deck-build && node build.js. Reads the slides array in build.js (slides are added to the deck in array order, NOT filename order) and writes docs/ab100-course-deck.pptx.
  • Sync: after every rebuild, also copy docs/ab100-course-deck.pptx over docs/ab100-course-deck-july-2026.pptx. The dated filename is the canonical artifact referenced from other docs; the undated one is just the build output.
  • Renderer constraint: html2pptx.js requires every text node be wrapped in <p>, <h1>-<h6>, <ul>, or <ol>. Bare text inside <div> or <span> fails the build with a validation error.
  • New slides: when adding a slide between existing ones, name it with a letter suffix (e.g. 05a-seg1-saas-first.html between 05 and 06) and add it to the slides array in build.js at the correct position. Do not renumber existing files.

Read the full file on GitHub · 182 lines

Changes

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.

  1. 5d ago First seen · 182 lines · 3,925 tokens per session scan A aca23eee2ab9

Subscribe to this mod's changes

ab100 CLAUDE.md is an instructions file published in the GitHub repository timothywarner-org/ab100 (37 stars, last pushed 1mo ago), licensed MIT. It adds 3,925 tokens to every session, about $0.0196 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.