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 agentmods add instructions/timothywarner-org/ab900/claude-mdgit 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/instructions/timothywarner-org/ab900/claude-md)<a href="https://agentmods.dev/instructions/timothywarner-org/ab900/claude-md"><img src="https://agentmods.dev/badge/instructions/timothywarner-org/ab900/claude-md.svg" alt="Measured on agentmods" 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 | $0.07662 | $0.07662 |
| Opus 5 | $0.03831 | $0.03831 |
| Sonnet 5 | $0.01532 | $0.01532 |
| Haiku 4.5 | $0.00766 | $0.00766 |
Grade A, and why
ab900 CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
cat /tmp/urls.txt | xargs -P 5 -I{} sh -c 'echo "$(curl -s -o /dev/null -w "%{http_code}" -L --max-time 20 -A "Mozilla/5.0" "{}") {}"' | grep -v '^200' How it starts
The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Purpose
This is a content-only repository for an AB-900 certification study buddy powered by GitHub Copilot agents, plus instructor materials for Tim Warner's O'Reilly Live Learning session. There is no application code, no build system, and no tests. The primary artifacts are agent definitions, skill specs, prompt templates, MCP server configurations, and distilled Microsoft Learn course content.
Architecture
.github/
agents/ab900-cert-buddy-agent.agent.md # Main Copilot agent definition
skills/
ab900-item-creator/SKILL.md # Exam question generation skill
ab900-scenario-walkthrough/SKILL.md # Scenario-based walkthrough skill
ab900-study-planner/SKILL.md # Personalized study plan skill
prompts/
ab900-practice-questions.prompt.md # Prompt template for practice questions
ab900-scenario-walkthrough.prompt.md # Prompt template for scenario walkthroughs
ab900-study-planner.prompt.md # Prompt template for personalized study plans
copilot-instructions.md # Copilot workspace instructions + rename table
workflows/
validate.yml # CI validation pipeline (non-blocking)
mlc-config.json # Markdown link checker config
.vscode/
mcp.json # MCP server definitions (workspace-scoped)
extensions.json # Recommended VS Code extensions
settings.json # VS Code workspace settings
docs/
module-01-security-foundations.md # Distilled from MS Learn: Zero Trust, Defender, Entra
module-02-core-services-admin.md # Distilled from MS Learn: admin center, Exchange/Teams/SP
module-03-data-protection-governance.md # Distilled from MS Learn: Purview, DLP, DSPM, eDiscovery
module-04-copilot-and-agents.md # Distilled from MS Learn: Copilot arch, agent types, licensing
module-05-copilot-admin-tasks.md # Distilled from MS Learn: license mgmt, PAYG, prompts
module-06-agent-admin-tasks.md # Distilled from MS Learn: agent creation, approval, lifecycle
demo-scripts.md # Live demo scripts for O'Reilly session
session-opener-governance.md # 10-min maker-spectrum + governance opener
exam-traps-cheatsheet.md # Common exam pitfalls, task-first lookup
portal-reference.md # Portals by exam DOMAIN, with verification caveats
PORTAL-CHEAT-SHEET.md # Portals by PORTAL, one block each, per-portal traps
new-features-deep-dive.md # Recent feature changes
session-agenda.md # Full session agenda
tenant-setup-guide.md # Lab tenant setup
(no deck here -- the single deck lives at the repo root)
references/
ab900-objectives.md # AB-900 skills-measured reference (current)
fictional-companies.md # Microsoft fictional company names for scenarios
style-guide.md # Microsoft Writing Style Guide key principles
shared-resources/
references/ # Exam guide, practice questions, skills breakdown
scripts/ # PowerShell helpers + demo-tenant provisioning
Deploy-AB900Foundry.ps1 # Azure AI Foundry demo env (idempotent, verified live)
Initialize-AB900PurviewDemo.ps1 # Purview DLP/labels/retention via Security & Compliance PS
templates/ # Deployment checklist, DLP policy template
slides/workspace/ # Deck build tooling (build-deck.js) + background assets
images/banner.png # README banner
segment-01-core-m365-services/ # Segment 1: demos, labs, slides, resources
segment-02-data-protection-governance/ # Segment 2: demos, labs, slides, resources
segment-03-copilot-administration/ # Segment 3: demos, labs, slides, resources
segment-04-agents-exam-prep/ # Segment 4: demos, labs, slides, resources
course-plan-july-2026.md # Live session plan (4 x 50-min segments)
warner-ab900-July-2026.pptx # THE deck -- exactly one, always at the root
README.md / QUICKSTART.md / FAQ.md # Repo front door and onboarding
CONTRIBUTING.md / LICENSE # Contribution guidance and license
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.
- 5d ago First seen · 343 lines · 7,662 tokens per session scan A e67dd8e929e0
ab900 CLAUDE.md is an instructions file published in the GitHub repository timothywarner-org/ab900 (26 stars, last pushed 1mo ago), licensed MIT. It adds 7,662 tokens to every session, about $0.0383 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
ab100 CLAUDE.md
Instructions for timothywarner-org/ab100, covering claude.md, repository purpose, slide deck build, source decks (microsoft ab-100t00) and course structure (4 hours).
ab100 copilot-instructions.md
Instructions for timothywarner-org/ab100, covering copilot instructions, repository purpose, key locations, skill and agent conventions and mcp server ids.
ab100 AGENTS.md
Instructions for timothywarner-org/ab100, covering agents.md, repository purpose, source of truth, course structure and poc app.
dp-800-study-guide CLAUDE.md
Instructions for kengio/dp-800-study-guide, covering claude.md, repository structure, practice quiz (practice/), currency policy and content guidelines.
Foundry-Local-Lab AGENTS.md
Instructions for microsoft-foundry/Foundry-Local-Lab, covering coding agent instructions, project overview, repository structure, language & framework details and python.
architect-ai CLAUDE.md
Instructions for aviraldua93/architect-ai, covering architectai — claude certified architect study tool, architecture, key patterns, exam domains and task statements.