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/grade)<a href="https://agentmods.dev/commands/timothywarner-org/ai901-cert-buddy-claude/grade"><img src="https://agentmods.dev/badge/commands/timothywarner-org/ai901-cert-buddy-claude/grade/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/grade"><img src="https://agentmods.dev/badge/commands/timothywarner-org/ai901-cert-buddy-claude/grade.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 | $0.00017 | $0.00228 |
| Opus 5 | $0.00009 | $0.00114 |
| Sonnet 5 | $0.00003 | $0.00046 |
| Haiku 4.5 | $0.00002 | $0.00023 |
Grade A, and why
grade 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
Grade the lab named: $ARGUMENTS
- Read
labs/<slug>/answer-key.json(the canonical key) andlabs/<slug>/submission.json(the learner's recorded results). If the submission file is missing, explain its shape: a JSON object that maps each checkidfrom the answer key to the value the learner observed, for example{ "resource_created": "yes", "ocr_text_found": "SHIP TO" }. - Call the cert-buddy MCP tool
grade_labwith the answer key and the submission. - Report the earned points, the percentage, and a per-check pass or fail list. For any miss, show the expected value next to the submitted value, and point back to the Microsoft Learn references in the lab so the learner can close the gap. Keep the tone encouraging.
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 · 12 lines · 17 tokens per session scan A 14c5635905be
grade is a command published in the GitHub repository timothywarner-org/ai901-cert-buddy-claude (9 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 228 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
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.