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.
git clone --depth 1 https://github.com/timothywarner-org/ai901-cert-buddy-claudeWrote 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.
[](https://agentmods.dev/commands/timothywarner-org/ai901-cert-buddy-claude/quiz)<a href="https://agentmods.dev/commands/timothywarner-org/ai901-cert-buddy-claude/quiz"><img src="https://agentmods.dev/badge/commands/timothywarner-org/ai901-cert-buddy-claude/quiz/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.
<a href="https://agentmods.dev/commands/timothywarner-org/ai901-cert-buddy-claude/quiz"><img src="https://agentmods.dev/badge/commands/timothywarner-org/ai901-cert-buddy-claude/quiz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00038 | $0.00665 |
| Opus 5 | $0.00019 | $0.00332 |
| Sonnet 5 | $0.00008 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
quiz 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 11d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use the ai901-cert-buddy subagent and the ai901-item-creator skill to run a short, exam-realistic AI-901 quiz.
Requested options (any may be blank): $ARGUMENTS
How many questions
count sets the number of questions. The default is 5. Use count=1 for a single question, up to count=10. This is a quiz, so deliver multiple questions by default and do not stop after the first one unless count=1.
If domain, bloom, or difficulty is missing, show the pick-list
A beginner cannot be expected to know these, so when an option is not supplied, show this short menu in plain language, apply sensible defaults to the whole quiz, and say in one line which defaults you used.
Domain (which half of the exam):
identify-- Identify AI concepts and capabilities (40-45%)implement-- Implement AI solutions by using Microsoft Foundry (55-60%)- default: a mix weighted by exam percentage across the quiz
Bloom level (how hard you have to think): Remember, Understand, Apply (default), Analyze.
Difficulty: easy | medium (default) | hard.
Run the quiz, one question at a time
For each question from 1 to count:
- Show progress as a header: "Question N of {count}".
- Ground the correct behavior in Microsoft Learn through the
ai901buddy-mslearnMCP server. - Phase 1: present the metadata, the scenario stem, and the four answer choices ONLY. Then stop and wait for my answer (a letter, or
hint, orskip). - Phase 2: after I answer, reveal the correct letter, a two-sentence rationale per choice, and the Microsoft Learn URLs. Keep a running tally, then continue to the next question.
Randomize the correct letter across A, B, C, and D, and the fictional company across the approved list, on every question. Do not repeat an objective within the same quiz.
End-of-quiz summary
After the final question, show a summary:
- Score: X of {count} correct, plus the percentage.
- A per-domain breakdown (Identify versus Implement).
- The two or three objectives to review next, each with a Microsoft Learn link, based on what I missed.
- One short, encouraging line on where to focus.
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.
- 11d ago First seen · 48 lines · 38 tokens per session scan A 5837f87390b6
quiz is a command published in the GitHub repository timothywarner-org/ai901-cert-buddy-claude (9 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 665 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 2026-08-31.
Other commands, from other repositories
audit-quiz-coverage
Find quiz coverage gaps from recent guide/CHANGELOG/CC-releases changes and propose new questions.
learn
Learn new capabilities through experimentation, then codify into the system.
explain
Explain the subject in depth using the fixed four-part structure: What, Why, Example, Consequences. Treat the subject as the thing to be explained, not as a literal question.
recap
Get a summary of everything you learned this session — concepts, quizzes, and progress.
learn
Capture a reusable learning from this session — with a dedup + Save/Absorb/Drop gate so the knowledge base stays clean.
interview
Prepare for the interview from the filed application — predicted questions, STAR answers from real evidence, and gap-defence.