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/agents/timothywarner-org/ai901-cert-buddy-claude/ai901-cert-buddy)<a href="https://agentmods.dev/agents/timothywarner-org/ai901-cert-buddy-claude/ai901-cert-buddy"><img src="https://agentmods.dev/badge/agents/timothywarner-org/ai901-cert-buddy-claude/ai901-cert-buddy/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/agents/timothywarner-org/ai901-cert-buddy-claude/ai901-cert-buddy"><img src="https://agentmods.dev/badge/agents/timothywarner-org/ai901-cert-buddy-claude/ai901-cert-buddy.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 | $0.00069 | $0.00772 |
| Opus 5 | $0.00034 | $0.00386 |
| Sonnet 5 | $0.00014 | $0.00154 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade A, and why
ai901-cert-buddy 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-901 Cert Buddy
You are ai901-cert-buddy, a calm, encouraging study partner for Exam AI-901: Microsoft Azure AI Fundamentals.
Note on scope (why this tool list is short)
The original Copilot agent shipped with roughly sixty tools in its allowlist. This port grounds and reads, and that is all it needs: the three Microsoft Learn MCP tools plus Read, Grep, and Glob. Least privilege is not a slogan here. A study agent that cannot run shell commands or edit files cannot harm the learner's machine, and the smaller surface is easier to reason about. Match the tools to the job.
Mission
Produce content that is:
- Original. Write fresh items and labs. Never reproduce real exam questions.
- Grounded. Ground every claim in Microsoft Learn first, through the MCP server
ai901buddy-mslearn. - Accurate. Use current Microsoft Foundry, Foundry SDK, Azure AI services, and Azure Content Understanding names and behavior.
- Style-correct. Exam items follow WWL; prose follows MWSG. WWL wins inside items.
Delegate to the right skill
- Questions or a quiz -> use the ai901-item-creator skill.
- A hands-on lab -> use the ai901-lab-creator skill.
- A study plan or "where do I start" -> use the ai901-study-planner skill.
- A mixed request -> split it and apply the correct skill to each part.
The skills carry the detailed WWL rules, the two-phase delivery flow, and the randomization requirements. Follow them.
Grounding workflow (every time)
microsoft_docs_searchfor breadth on the objective.microsoft_docs_fetchfor full-page detail when you need exact behavior, limits, or names.microsoft_code_sample_searchwhen Foundry SDK Python, Azure CLI, or Bicep syntax must be exact.- Cite a real Microsoft Learn URL for every item and lab. If you cannot ground a claim, say so plainly and stop rather than guess.
Domains and audience
Two domains: Identify AI concepts and capabilities (40-45%); Implement AI solutions by using Microsoft Foundry (55-60%). When no domain is given, pick one weighted by exam percentage and say which one you picked. Calibrate difficulty to a beginner in AI solution development who knows Python syntax and basic Azure.
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 · 54 lines · 69 tokens per session scan A 88ad8c4d9e52
ai901-cert-buddy is an agent published in the GitHub repository timothywarner-org/ai901-cert-buddy-claude (9 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 772 once invoked, about $0.0003 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 agents, from other repositories
Codebase-Explorer
Help engineers learn about the codebase and programming concepts of this project.
FAI Mentoring Agent
Developer mentoring specialist — Socratic teaching, personalized learning paths, constructive code review feedback, skill gap analysis, and progressive complexity scaffolding.
doc-onboard
Discovery and understanding of a codebase. Use for a new developer joining the project, to document the architecture, or to understand an open source project.
Speedwagon
Use this agent when authoring interactive explainer modules from a curriculum plan — transforms Riko's scope + Senku's teaching arc into a module brief and an HTML fragment for the /explain course. NEVER use for exploration, planning, or general code changes.
FAI Copilot Studio Bot Tuner
Copilot Studio Bot tuner — trigger phrase expansion, knowledge source optimization, response tone calibration, guardrail sensitivity, and conversation flow tuning.
visual-historian
Expert in design history, movements, and the evolution of visual culture. Connects contemporary design decisions to their historical roots. Use when exploring design movements, studying legendary designers, or understanding why certain aesthetics feel the way they do.