az104-cert-buddy: Instructions file for Claude Code

CLAUDE.md

az104-cert-buddy CLAUDE.md is an instructions file for Claude Code from timothywarner-org/az104-cert-buddy. It costs 1,169 tokens per session, scanned A, original, MIT.

A set of instructions for an AZ-104 certification study repository. AZ-104 is Microsoft's associate-level Azure administrator exam, and the repository contains study agents, prompts, and reference connections rather than application code.

In plain words
What is it for?
Creating realistic Azure practice questions, short self-checking labs, and personalised study plans across five exam areas.
Why use it?
It gives coding agents the project structure and rules needed to work with the study materials correctly. It also points them to the required learning sources and explains a key skill-discovery issue.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is timothywarner-org/az104-cert-buddy's own configuration. It tells Claude Code how to work on az104-cert-buddy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything az104-cert-buddy configures →

Reuse

Borrowing it

Nothing to install: this file belongs to timothywarner-org/az104-cert-buddy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/timothywarner-org/az104-cert-buddy/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/timothywarner-org/az104-cert-buddy

Made for: Claude Code.

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 az104-cert-buddy CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/timothywarner-org/az104-cert-buddy/claude-md/github.svg)](https://agentmods.dev/instructions/timothywarner-org/az104-cert-buddy/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/timothywarner-org/az104-cert-buddy/claude-md"><img src="https://agentmods.dev/badge/instructions/timothywarner-org/az104-cert-buddy/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.

agentmods 80×15 button for az104-cert-buddy CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/timothywarner-org/az104-cert-buddy/claude-md"><img src="https://agentmods.dev/badge/instructions/timothywarner-org/az104-cert-buddy/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,169 This file is loaded in full into every session.
When invoked 1,169 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01169 $0.01169
Opus 5 $0.00584 $0.00584
Sonnet 5 $0.00234 $0.00234
Haiku 4.5 $0.00117 $0.00117

Measured 9d ago against content hash a11c636b8ce9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

az104-cert-buddy 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 9d 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 · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 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

Content-only repository for an AZ-104 certification study buddy powered by GitHub Copilot agents. No application code, no build system, no tests. Artifacts are agent definitions, skill specs, prompt templates, and MCP server configurations.

Architecture

The az104-cert-buddy-agent (.github/agents/) orchestrates three auto-discovered skills (.github/skills/):

  • az104-item-creator -- Exam-realistic practice questions with two-phase interactive delivery (question first, rationale after user answers). Supports "hint" and "skip" commands.
  • az104-lab-creator -- 10-20 minute self-validating labs with validation gates and mandatory cleanup.
  • az104-study-planner -- Personalized study plans based on confidence self-assessment across five AZ-104 skill areas.

Three prompt templates (.github/prompts/) provide slash-command entry points: /az104-practice-question, /az104-practice-lab, /az104-study-planner.

All content is grounded via a single MCP server: az104buddy-mslearn (https://learn.microsoft.com/api/mcp, free, no API key) providing microsoft_docs_search, microsoft_docs_fetch, and microsoft_code_sample_search.

A parallel AB-900 cert buddy implementation lives in reference/ as a template. Do not modify it when editing AZ-104 files.

Skill Discovery (Critical Gotcha)

GitHub Copilot does not support a skills: field in agent YAML frontmatter. Skills are auto-discovered from .github/skills/ folders based on name and description in SKILL.md frontmatter. The agent references skills by name in its Markdown body only.

Cross-Reference Dependencies

When renaming anything, update all dependents:

  • Agent name field -> all .github/prompts/*.prompt.md agent: fields
  • Skill name field -> agent Markdown body references
  • MCP server ID in .vscode/mcp.json -> agent and prompt tools: lists

Read the full file on GitHub · 86 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. 9d ago First seen · 86 lines · 1,169 tokens per session scan A a11c636b8ce9

Subscribe to this mod's changes

az104-cert-buddy CLAUDE.md is an instructions file published in the GitHub repository timothywarner-org/az104-cert-buddy (22 stars, last pushed 5mo ago), licensed MIT. It adds 1,169 tokens to every session, about $0.0058 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.