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/lab)<a href="https://agentmods.dev/commands/timothywarner-org/ai901-cert-buddy-claude/lab"><img src="https://agentmods.dev/badge/commands/timothywarner-org/ai901-cert-buddy-claude/lab/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/lab"><img src="https://agentmods.dev/badge/commands/timothywarner-org/ai901-cert-buddy-claude/lab.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 | $0.00024 | $0.00407 |
| Opus 5 | $0.00012 | $0.00204 |
| Sonnet 5 | $0.00005 | $0.00081 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
lab 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 10d 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.
What it actually says
Use the ai901-lab-creator skill to build a short, hands-on Microsoft Foundry lab on: $ARGUMENTS
If no topic is given, offer a pick-list
Show four or five beginner-friendly AI-901 lab topics, one per AI workload (language, speech, vision, document or content understanding, and a Foundry agent), then let the learner pick or choose one and say which.
Emit a gradable lab document
Save the lab under labs/<slug>/ as TWO files so it can be auto-graded later with /grade:
labs/<slug>/lab.md-- the learner-facing lab: objective, prerequisites, numbered steps (keyless auth via Microsoft Entra ID withDefaultAzureCredential), validation gates, troubleshooting, and a mandatory cleanup step.labs/<slug>/answer-key.json-- the canonical answer key a grader compares against. Follow the schema inlabs/README.md: achecksarray where each entry hasid,description,expected, andpoints, plus atotal_pointsfield.
Ground every step, service name, and code sample in Microsoft Learn first, and cite the URLs in lab.md. When done, tell the learner where the two files were saved and that they can run /grade <slug> once they have recorded their results in labs/<slug>/submission.json.
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.
- 10d ago First seen · 21 lines · 24 tokens per session scan A f6ebe593497b
lab is a command published in the GitHub repository timothywarner-org/ai901-cert-buddy-claude (9 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 407 once invoked, about $0.0001 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
learn
Learn new capabilities through experimentation, then codify into the system.
recap
Get a summary of everything you learned this session — concepts, quizzes, and progress.
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.
interview
Prepare for the interview from the filed application — predicted questions, STAR answers from real evidence, and gap-defence.
learn
Capture a reusable learning from this session — with a dedup + Save/Absorb/Drop gate so the knowledge base stays clean.
explain
Generate an interactive one-module explainer for a topic — Riko gathers code scope, Senku plans a 3-5 screen teaching arc, Speedwagon authors the HTML, assembler produces explain-out/index.html.