ab100: Skill for Claude Code

.github/skills/ab100-lab-creator/SKILL.md

ab100-lab-creator is a skill for Claude Code, Codex from timothywarner-org/ab100. It costs 90 tokens per session (3,054 once invoked), scanned A, original, MIT.

A skill for creating short AB-100 practice labs. AB-100 is a Microsoft certification exam about building and managing AI agents, and the labs cover tools such as Copilot Studio and Microsoft Foundry.

In plain words
What is it for?
Use it to create 15–25 minute labs for agent design, Copilot Studio, Microsoft Foundry, deployment and lifecycle management, or governance.
Why use it?
It turns study topics into exercises that can be run and checked, with clear prerequisites, expected results, and cleanup instructions. This helps learners practise rather than only read explanations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is timothywarner-org/ab100's own configuration. It tells Claude Code and Codex how to work on ab100 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 ab100 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to timothywarner-org/ab100. 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/ab100/main/.github/skills/ab100-lab-creator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/timothywarner-org/ab100

Made for: Claude Code, Codex.

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-lab-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/timothywarner-org/ab100/ab100-lab-creator/github.svg)](https://agentmods.dev/skills/timothywarner-org/ab100/ab100-lab-creator)
Your own site
<a href="https://agentmods.dev/skills/timothywarner-org/ab100/ab100-lab-creator"><img src="https://agentmods.dev/badge/skills/timothywarner-org/ab100/ab100-lab-creator/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 ab100-lab-creator

Your own site · 80×15
<a href="https://agentmods.dev/skills/timothywarner-org/ab100/ab100-lab-creator"><img src="https://agentmods.dev/badge/skills/timothywarner-org/ab100/ab100-lab-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,054 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00090 $0.03054
Opus 5 $0.00045 $0.01527
Sonnet 5 $0.00018 $0.00611
Haiku 4.5 $0.00009 $0.00305

Measured 9d ago against content hash 03fe3f651a0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ab100-lab-creator 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.

.github/skills/ab100-lab-creator/SKILL.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: ab100.practice_labs.micro.validated

Description: Create short AB-100 practice labs (15-25 minutes) that are executable and self-validating. Every lab includes prerequisites, exact tasks, validation steps, expected outputs, and cleanup.

Style precedence

Follow the Microsoft Worldwide Learning Exam Writing Style Guide (WWL) for any text that mirrors exam phrasing (titles, goal statements, named resources, company references). Follow the Microsoft Writing Style Guide (MWSG) for the lab prose itself: warm, scannable, present-tense, sentence-style capitalization. Two MWSG conventions overridden by WWL for our labs: no contractions and all uppercase for key names (TAB, ENTER, CTRL+ALT+DELETE).

Lab categories

AB-100 labs span four practical categories:

  • Agent authoring -- Copilot Studio topic and agent flow creation, Foundry agent manifests, declarative agents in Microsoft 365 Copilot.
  • Design walkthrough -- structured design review against the Power Platform Well-Architected framework, pattern selection (task vs autonomous vs prompt/response), build/buy/extend decision matrices.
  • ALM -- Copilot Studio solution export and import, Power Platform Build Tools pipelines, Microsoft Foundry environment promotion, Dynamics 365 AI feature configuration migration.
  • Responsible AI and governance -- DLP policies, environment strategy, agent security configuration, audit trail setup, responsible AI review checklist.

Default authoring tools: Copilot Studio (UI or YAML), Microsoft Foundry portal, Power Platform admin center, Power Platform CLI. Avoid labs that require production-only Dynamics 365 modules unless the user confirms access.

Grounding

Required sources:

  • Microsoft Learn (truth source for architecture and correct configuration). Access via the Microsoft Learn MCP server using microsoft_docs_search and microsoft_docs_fetch.
  • Microsoft Learn code samples (for Copilot Studio YAML, Power Platform CLI, Microsoft Foundry SDK, Bicep accuracy). Access via microsoft_code_sample_search.
  • Canonical AB-100 skills outline: docs/ab100-exam-objectives.md.

Read the full file on GitHub · 257 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 · 257 lines · 90 tokens per session scan A 03fe3f651a0c

Subscribe to this mod's changes

ab100-lab-creator is a skill published in the GitHub repository timothywarner-org/ab100 (37 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 3,054 once invoked, about $0.0005 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.