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.
npx skills add timothywarner-org/ai901-cert-buddy-claude --skill ai901-item-creatorgit 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/skills/timothywarner-org/ai901-cert-buddy-claude/ai901-item-creator)<a href="https://agentmods.dev/skills/timothywarner-org/ai901-cert-buddy-claude/ai901-item-creator"><img src="https://agentmods.dev/badge/skills/timothywarner-org/ai901-cert-buddy-claude/ai901-item-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.
<a href="https://agentmods.dev/skills/timothywarner-org/ai901-cert-buddy-claude/ai901-item-creator"><img src="https://agentmods.dev/badge/skills/timothywarner-org/ai901-cert-buddy-claude/ai901-item-creator.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 | $0.00092 | $0.04913 |
| Opus 5 | $0.00046 | $0.02457 |
| Sonnet 5 | $0.00018 | $0.00983 |
| Haiku 4.5 | $0.00009 | $0.00491 |
Grade A, and why
ai901-item-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 12d 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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: ai901.practice_questions.exam_realistic
Description: Generate AI-901 practice questions that feel like the real Microsoft Azure AI Fundamentals exam without copying it. Every item is grounded in current Microsoft Learn content, uses modern Microsoft product names, and follows Microsoft-style exam item rules: scenario-first stems, plausible distractors, parallel choices, no trick wording.
Exam facts (canonical)
- Exam: AI-901 -- Microsoft Azure AI Fundamentals (Microsoft Press video course companion)
- Skills measured date: April 15, 2026
- Pass score: 700
- Study guide URL: https://learn.microsoft.com/credentials/certifications/resources/study-guides/ai-901
- Audience profile: candidates at the beginning of their career in AI solution development, with conceptual knowledge of AI in Azure, Python coding syntax, and familiarity with Azure resources.
Style precedence
The Microsoft Worldwide Learning Exam Writing Style Guide (WWL) is authoritative for every item. The Microsoft Writing Style Guide (MWSG) governs prose voice and tone where WWL is silent. When the two guides conflict, WWL wins.
Two MWSG conventions overridden by WWL for exam items:
- No contractions anywhere in an item.
- All uppercase for key names: TAB, ENTER, CTRL+ALT+DELETE.
Grounding
Required sources:
- Microsoft Learn (truth source for objectives and product behavior). Access via the Microsoft Learn MCP server
ai901buddy-mslearnusingmicrosoft_docs_searchandmicrosoft_docs_fetch. - Microsoft Learn code samples (for Microsoft Foundry SDK, Azure AI Language, Azure AI Speech, Azure AI Vision, and Azure Content Understanding accuracy). Access via
microsoft_code_sample_search. - Canonical AI-901 objective domain file:
.claude/skills/_references/ai901-objective-domain.md(verbatim mirror, dated 2026-05-05).
Grounding-first rule: query the Microsoft Learn MCP before any other source. Never substitute generic web search.
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.
- 12d ago First seen · 370 lines · 92 tokens per session scan A b66268337a65
ai901-item-creator is a skill published in the GitHub repository timothywarner-org/ai901-cert-buddy-claude (9 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 4,913 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 2026-08-31.
Other skills, from other repositories
nanogpt
Educational GPT implementation in 300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
rwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
context-manager
Gestion avancée du contexte pour agents IA — fenêtre de contexte, compression, RAG dynamique, sliding window, prompt caching. Se déclenche avec "context window", "contexte agent", "token limit", "context management", "context overflow", "trop de contexte", "agent context", "context stuffing", "context compression".…
data-analyst-agent
Création d'agents d'analyse de données qui explorent, visualisent et expliquent les données. Se déclenche avec "data analyst agent", "agent analyse données", "agent data", "agent qui analyse", "automated analysis", "data exploration agent", "agent SQL", "agent pandas". Also triggers on "agent that analyzes data"…
mcp-server-builder
Création de serveurs MCP (Model Context Protocol) pour exposer des outils, ressources et prompts aux LLMs. Se déclenche avec "MCP", "Model Context Protocol", "MCP server", "MCP tool", "MCP resource", "serveur MCP", "connecter Claude à", "exposer une API à Claude", "claude desktop config". Also triggers on "build an…
openai-assistants-builder
Création d'assistants IA hébergés avec l'API OpenAI Assistants v2. File search avec vector stores, code interpreter, function calling, threads persistants et streaming. Se déclenche avec "OpenAI Assistants", "assistant API", "file search", "code interpreter", "thread", "run", "assistant OpenAI", "GPT assistant"…