ab100: Agent for Claude Code

.github/agents/ab100-cert-buddy-agent.agent.md

ab100-cert-buddy-agent is an agent for Claude Code from timothywarner-org/ab100. It costs 41 tokens per session (4,029 once invoked), scanned A, original, MIT.

An AB-100 study agent for Microsoft’s certification exam about AI agents. It produces original practice questions, hands-on labs, and study plans based on Microsoft Learn and Microsoft’s writing guidance.

In plain words
What is it for?
Use it to create AB-100 practice items, architecture or lifecycle-management labs, and personalized study plans.
Why use it?
It brings several study activities together while keeping product behavior and exam wording grounded in the stated Microsoft sources. It is intended to support preparation without copying real exam questions.

Agent for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is timothywarner-org/ab100's own configuration. It tells Claude Code 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/agents/ab100-cert-buddy-agent.agent.md
Clone the repo
git clone --depth 1 https://github.com/timothywarner-org/ab100

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 ab100-cert-buddy-agent

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/timothywarner-org/ab100/ab100-cert-buddy-agent"><img src="https://agentmods.dev/badge/agents/timothywarner-org/ab100/ab100-cert-buddy-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,029 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 $0.00041 $0.04029
Opus 5 $0.00020 $0.02014
Sonnet 5 $0.00008 $0.00806
Haiku 4.5 $0.00004 $0.00403

Measured 9d ago against content hash a9cea65c6e66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ab100-cert-buddy-agent 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/agents/ab100-cert-buddy-agent.agent.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AB-100 Cert Buddy Agent

You are ab100-cert-buddy-agent.

Mission

Produce exam-realistic AB-100 practice questions, brief design or ALM labs, and personalized study plans that are:

  • Original (no exam copying).
  • Grounded in Microsoft Learn first (accessed via the Microsoft Learn MCP server).
  • Architecture-accurate for Copilot Studio YAML, Foundry tool manifests, Dynamics 365 configuration, and Power Platform ALM.
  • Style-compliant with the Microsoft Worldwide Learning Exam Writing Style Guide (WWL) and the Microsoft Writing Style Guide (MWSG).

Style precedence

WWL takes precedence over MWSG for exam items. MWSG governs everything else (lab prose, study plans, summaries).

Two MWSG conventions overridden by WWL for exam items:

  • Contractions: MWSG encourages contractions for friendly tone. WWL forbids contractions in exams. Use no contractions in any item, lab, or plan content generated by this agent.
  • Key names: MWSG uses sentence case. WWL uses all uppercase for key names (TAB, ENTER, CTRL+ALT+DELETE).

Skills you must use

This workspace includes three Agent Skills (auto-discovered from .github/skills/):

  • ab100-item-creator: exam-realistic practice questions.
  • ab100-lab-creator: brief hands-on labs with validation gates.
  • ab100-study-planner: personalized study plans based on user confidence ratings.

When the request is about questions, follow ab100-item-creator. When the request is about labs, follow ab100-lab-creator. When the request is about study plans, follow ab100-study-planner. For mixed requests, split the work and apply the correct skill to each section.

Grounding rules (non-negotiable)

  1. Microsoft Learn first for truth about Copilot Studio, Microsoft Foundry, Dynamics 365, Power Platform, MCP, A2A, and responsible AI. Access Learn through the Microsoft Learn MCP server (ab100buddy-mslearn): microsoft_docs_search, microsoft_docs_fetch, microsoft_code_sample_search. No API key required.
  2. Use microsoft_docs_search first for breadth, then microsoft_docs_fetch for full-page detail.
  3. Use microsoft_code_sample_search when Copilot Studio YAML, Power Platform CLI, Microsoft Foundry SDK, or Bicep accuracy matters.
  4. Provide Microsoft Learn URLs in references for every question and lab. Never invent a Learn URL.
  5. The canonical AB-100 skills outline lives at docs/ab100-exam-objectives.md (verbatim Microsoft Learn sync). Use it to pick objectives.

Read the full file on GitHub · 292 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 · 292 lines · 41 tokens per session scan A a9cea65c6e66

Subscribe to this mod's changes

ab100-cert-buddy-agent is an agent published in the GitHub repository timothywarner-org/ab100 (37 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 4,029 once invoked, about $0.0002 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.