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/copilot-instructionsgit 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/copilot-instructions)<a href="https://agentmods.dev/instructions/timothywarner-org/ab900/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/timothywarner-org/ab900/copilot-instructions.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 | $0.02254 | $0.02254 |
| Opus 5 | $0.01127 | $0.01127 |
| Sonnet 5 | $0.00451 | $0.00451 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
ab900 copilot-instructions.md 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 3d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot instructions
Repository purpose
- This repo defines GitHub Copilot agent behavior and AB-900 skills. There is no app code; the primary artifacts are agent definitions and skill specs.
Key locations
- Agent definition: .github/agents/ab900-cert-buddy-agent.agent.md
- Skills: .github/skills/*/SKILL.md
- Prompts: .github/prompts/ab900-practice-questions.prompt.md, .github/prompts/ab900-scenario-walkthrough.prompt.md, .github/prompts/ab900-study-planner.prompt.md
- MCP servers (workspace only): .vscode/mcp.json
Skill and agent conventions
- Each skill file is a single YAML frontmatter block followed by Markdown.
- The skill name used by agents must match the YAML frontmatter name in the skill file, not the folder name.
- Agent files use YAML frontmatter with tools and skills lists. Keep tool IDs scoped to MCP servers defined in .vscode/mcp.json.
- Prompt files (in .github/prompts/) reference agents by the
namefield in the agent's YAML frontmatter via theagent:key. The current value isab900-cert-buddy-agent. If the agent is renamed, update all prompt files that reference it. - Current skills:
- ab900-item-creator (exam item generation)
- ab900-scenario-walkthrough (scenario-based walkthrough delivery)
- ab900-study-planner (personalized study plan generation)
Grounding and validation rules
- Questions must be grounded in Microsoft Learn content first. Use the Microsoft Learn MCP server (mcp__claude_ai_Microsoft_Learn_MCP_Server) to retrieve current Learn documentation when available; this server provides microsoft_docs_search and microsoft_docs_fetch tools for grounding content in official MS Learn documentation.
- Use Context7 (ab900buddy-context7) when M365 admin PowerShell or Graph API syntax accuracy matters.
- Use MarkItDown (ab900buddy-markitdown) to convert user-supplied PDFs or Office documents to markdown for analysis.
- If a request mixes questions and scenario walkthroughs, split the output and apply the correct skill to each section.
- Grounding chain: Microsoft Learn first (via MS Learn MCP or web search) -> Context7 for M365 admin syntax -> MarkItDown for user documents.
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.
- 3d ago First seen · 145 lines · 2,254 tokens per session scan A e374a091825f
ab900 copilot-instructions.md is an instructions file published in the GitHub repository timothywarner-org/ab900 (26 stars, last pushed 1mo ago), licensed MIT. It adds 2,254 tokens to every session, about $0.0113 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 2026-08-30.
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 AGENTS.md
Instructions for timothywarner-org/ab100, covering agents.md, repository purpose, source of truth, course structure and poc app.
ab100 copilot-instructions.md
Instructions for timothywarner-org/ab100, covering copilot instructions, repository purpose, key locations, skill and agent conventions and mcp server ids.
claude-certified-architect CLAUDE.md
Claude Code instructions for magnusrodseth/claude-certified-architect, covering claude.md, key commands, architecture and conventions.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).