dp-800-study-guide CLAUDE.md

dp-800-study-guide CLAUDE.md is an instructions file for coding agents from kengio/dp-800-study-guide. It costs 3,216 tokens per session, scanned A, original, MIT.

Repository instructions for a public study guide for Microsoft's DP-800 certification, an exam about developing AI-enabled database solutions. They describe the guide's folders, contribution expectations, currency policy and content rules.

In plain words
What is it for?
Use them when adding or editing certification lessons, practice quizzes or database topics, checking claims against Microsoft's official exam outline and preparing community contributions.
Why use it?
They help contributors keep study material accurate, current and suitable for a public project where changes are reviewed through pull requests.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/kengio/dp-800-study-guide/claude-md
Clone the repo
git clone --depth 1 https://github.com/kengio/dp-800-study-guide

Wrote 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.

agentmods badge for dp-800-study-guide CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kengio/dp-800-study-guide/claude-md.svg)](https://agentmods.dev/instructions/kengio/dp-800-study-guide/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kengio/dp-800-study-guide/claude-md"><img src="https://agentmods.dev/badge/instructions/kengio/dp-800-study-guide/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,216 This file is loaded in full into every session.
When invoked 3,216 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.03216 $0.03216
Opus 5 $0.01608 $0.01608
Sonnet 5 $0.00643 $0.00643
Haiku 4.5 $0.00322 $0.00322

Measured 5d ago against content hash 9861b9cb9914, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dp-800-study-guide CLAUDE.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 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.

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.

CLAUDE.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Open-source community study guide for the Microsoft DP-800: Developing AI-Enabled Database Solutions certification exam. Licensed under MIT (see LICENSE). Aligned to the official skills-measured list updated March 12, 2026.

The repository is public; contributions arrive as pull requests. Keep this in mind: every change is visible to the community. Prefer additive, well-justified edits over silent rewrites, and verify factual claims against the official skills measured page before merging.

Repository Structure

dp-800-study-guide/
├── certification/
│   ├── dp-800-overview.md      # Certification index with exam overview and progress tracker
│   ├── 01-database-objects/    # Design and implement database objects
│   ├── 02-programmability-objects/ # Views, functions, stored procedures, triggers
│   ├── 03-advanced-tsql/       # CTEs, window functions, JSON, regex, graph queries
│   ├── 04-ai-assisted-tools/   # GitHub Copilot, MCP, AI security
│   ├── 05-data-security-compliance/ # Encryption, masking, RLS, auditing
│   ├── 06-performance-optimization/ # Configs, isolation levels, query plans
│   ├── 07-cicd-database-projects/   # SQL Database Projects, CI/CD, deployment
│   ├── 08-azure-services-integration/ # DAB, REST/GraphQL, monitoring, CDC
│   ├── 09-models-embeddings/   # External models, embedding generation
│   ├── 10-intelligent-search/  # Full-text, vector, and hybrid search
│   ├── 11-rag/                 # Retrieval-augmented generation
│   └── resources/              # Practice questions, mock exams, exam tips, code examples, appendix, cheat sheets
├── i18n/                       # Community translations — parallel tree per locale, see TRANSLATING.md
├── practice/                   # Static adaptive practice quiz — HTML/JS/CSS + Python build.py + JSON banks

Each topic folder contains a named index file (e.g., database-objects.md, advanced-tsql.md) and numbered .md topic files.

Read the full file on GitHub · 201 lines

Changes

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.

  1. 5d ago First seen · 201 lines · 3,216 tokens per session scan A 9861b9cb9914

Subscribe to this mod's changes

dp-800-study-guide CLAUDE.md is an instructions file published in the GitHub repository kengio/dp-800-study-guide (21 stars, last pushed 1mo ago), licensed MIT. It adds 3,216 tokens to every session, about $0.0161 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.