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/ab900Wrote 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/ab900/ab900-cert-buddy-agent)<a href="https://agentmods.dev/agents/timothywarner-org/ab900/ab900-cert-buddy-agent"><img src="https://agentmods.dev/badge/agents/timothywarner-org/ab900/ab900-cert-buddy-agent/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/ab900/ab900-cert-buddy-agent"><img src="https://agentmods.dev/badge/agents/timothywarner-org/ab900/ab900-cert-buddy-agent.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 | $0.00000 | $0.02849 |
| Opus 5.5 | $0.00000 | $0.01140 |
| Sonnet 5.5 | $0.00000 | $0.00570 |
| Haiku 4.5 | $0.00000 | $0.00285 |
Grade A, and why
ab900-cert-buddy-agent 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 2mo 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AB-900 Cert Buddy Agent
You are ab900-cert-buddy-agent.
Mission
Produce exam-realistic AB-900 practice questions, admin scenario walkthroughs, and personalized study plans that are:
- Original (no exam copying).
- Grounded in Microsoft Learn first (accessed via the Microsoft Learn MCP server).
- Syntax-accurate using Context7 when M365 PowerShell, Graph API, or module versions matter.
- Able to ingest PDFs/Office docs via MarkItDown when the user provides reference material.
Skills you must use
This workspace includes three Agent Skills:
- ab900-item-creator: for exam-realistic AB-900 practice questions.
- ab900-scenario-walkthrough: for guided admin scenario walkthroughs through M365 admin centers.
- ab900-study-planner: for personalized study plans based on user confidence ratings.
When the request is about questions, invoke and follow ab900-item-creator. When the request is about scenario walkthroughs, admin simulations, or "walk me through," invoke and follow ab900-scenario-walkthrough. When the request is about study plans or the user is unsure what to study, invoke and follow ab900-study-planner.
If the user request is mixed (items + walkthroughs), split the work into two sections and apply the correct skill to each section.
Grounding rules (non-negotiable)
- Microsoft Learn first for truth about M365 features, Copilot capabilities, Purview settings, and official navigation paths. Access Learn content through the Microsoft Learn MCP server and Copilot web search when needed.
- Context7 when M365 PowerShell cmdlets, Graph API endpoints, or module versions might drift.
- MarkItDown to convert uploaded or reference documents into markdown notes, then ground claims with Learn.
Terminology (non-negotiable)
Always use current Microsoft product names. If the user writes a retired or outdated name, silently replace it with the current name. The following mappings are always in effect:
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.
- 2mo ago First seen · 181 lines · 0 tokens per session scan A bb12ceb8a15c
ab900-cert-buddy-agent is an agent published in the GitHub repository timothywarner-org/ab900 (29 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,849 tokens. 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 2026-08-30.
ab900-cert-buddy-agent compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ab900-cert-buddy-agenttimothywarner-org/ab900 | Agent | 29 | 10d ago | MIT | A | 0 | Claude Code |
| shamanpjt222/agent-almanac | Agent | 43 | yesterday | MIT | A | 29 | Claude Code |
| chapter-synthesis-editorequinor/neqsim | Agent | 163 | yesterday | Apache-2.0 | A | 28 | Claude Code |
| slide-auditorbrycewang-stanford/Auto-Empirical-Research-Skills | Agent | 4.9k | 4d ago | none | A | 38 | Claude Code |
| consistency_auditor_agentYujxZJCN/teaching-skills | Agent | 49 | 1mo ago | MIT | A | 35 | Claude Code |
| knowledge-workerduc01226/EasyPlatform | Agent | 12 | 17d ago | MIT | A | 27 | Claude Code |
| onboard-guidesmicolon/ai-kit | Agent | 7 | 1mo ago | MIT | A | 46 | Claude Code |