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/commands/timothywarner-org/ab900/ab900-scenario-walkthrough)<a href="https://agentmods.dev/commands/timothywarner-org/ab900/ab900-scenario-walkthrough"><img src="https://agentmods.dev/badge/commands/timothywarner-org/ab900/ab900-scenario-walkthrough/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/ab900/ab900-scenario-walkthrough"><img src="https://agentmods.dev/badge/commands/timothywarner-org/ab900/ab900-scenario-walkthrough.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 | $0.00045 | $0.01141 |
| Opus 5.5 | $0.00018 | $0.00456 |
| Sonnet 5.5 | $0.00009 | $0.00228 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
ab900-scenario-walkthrough 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 9d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AB-900 Scenario Walkthrough
Generate ONE realistic AB-900 admin scenario walkthrough.
Use this skill
You must follow the workspace skill ab900-scenario-walkthrough for walkthrough structure, guardrails, AB-900 accuracy rules, output format, and delivery rules (full walkthrough in a single message).
Inputs (from chat)
- Domain: ${input:domain:Domain 1 | Domain 2 | Domain 3 (or leave blank and the agent picks one)}
- Scenario type: ${input:scenarioType:Copilot licensing | Agent approval | DSPM for AI review | SharePoint oversharing | Sensitivity labels | DLP policy | PIM/Conditional Access}
- Estimated time: ${input:estimatedTime:5 min | 10 min (default 10 min)}
Grounding and validation rules
- Ground every navigation path and setting in Microsoft Learn using the Microsoft Learn MCP server and Copilot web search. Microsoft Learn is the primary grounding source for all admin center paths and feature behavior.
- If the walkthrough includes M365 PowerShell cmdlets or Graph API calls, confirm command names and parameters with Context7 tools.
- Provide Microsoft Learn URLs in the references section of the walkthrough output.
Terminology
Always use current Microsoft product names. Apply all mappings from the agent terminology table silently. Never use:
- "Azure AD", "AAD", or "Azure Active Directory" (use "Microsoft Entra ID")
- "compliance.microsoft.com" (use "purview.microsoft.com")
- "AI hub" (use "DSPM for AI")
- "Azure AI Studio" (use "Microsoft Foundry")
- "Microsoft 365 Defender" (use "Microsoft Defender XDR"; the portal is the "Microsoft Defender portal")
- "Exchange Online admin center" (use "Exchange admin center")
- "Content explorer" where the current tool is "Data explorer"
- "Requested agents tab" (use "Requests")
- "Billing > Billing policies" for Copilot (use "Copilot > Billing & usage")
- "restricted site access" as the primary term (use "restricted access control"; note that the SharePoint admin center UI does label the per-site section "Restricted site access")
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.
- 9d ago First seen · 76 lines · 45 tokens per session scan A 4cba635b6954
ab900-scenario-walkthrough is a command published in the GitHub repository timothywarner-org/ab900 (29 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 1,141 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-20.
Other commands, from other repositories
graph
Extract prerequisite concept graph from converted course materials and write course-index/concept-graph.md.
alt
Import an Exam Radar (OPTIMETA Alt plugin) export and fold its lecture-emphasis exam signal into the course index — radar.md, a lecture-emphasis column on coverage.md, and a gold-zone weakmap.
quiz
Generate N practice problems on a topic. Saves problem MD + hidden answer MD. User solves on paper, uploads answer PDF, then runs /grade. First arg weakmap → auto-load latest weakmap report and target its top weaknesses.
weakmap
Priority-ranked weakness report. No arg → fresh report from latest errors per pattern. With concept arg → patch latest report by adding the user-declared weakness, save as new timestamped file.
derive
Save a clean reference derivation of a target equation or theorem to derivations/. Draws from course materials (textbook, lecture notes) rather than testing the user.
mock
Generate a mock exam matched to the course's structure (inferred from course-index). Saves problem MD + hidden solution MD. User solves on paper, uploads PDF, runs /grade.