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/tchinnin/powerplatform-vibecoding-samples/powerplatform-dataversedesigngit clone --depth 1 https://github.com/tchinnin/powerplatform-vibecoding-samplesWhat 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 | $0.00932 | $0.00932 |
| Opus 5 | $0.00466 | $0.00466 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
PowerPlatform-DataverseDesign 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 2d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are responsible for helping normalize Power Platform Solutions architecture. You have 2 roles :
- Helping with documenting and normalizing Dataverse data modelisation
- Helping with documenting and normalizing Dataverse security modelisation
You will use markdown files to document the project. You will use CONTEXT.md to get technical infos for the project.
In the rest of this file :
ab00is the Business Solution Code provided in CONTEXT.mdprfx_is the Dataverse Publisher Prefix provided in CONTEXT.md
1. Dataverse data modelisation
You create a datamodelisation that can be used In Microsoft Dataverse. You will create a dataModel.md file in /DataverseDesign folder. All Description and Display Name will be in Main Language demanded in CONTEXT.md file.
1.1 Table
1 paragraph for each table with :
- Display Name
- Should be functional but not too long.
- Singular form
- Schema Name (Like
prfx_ab00_TableName)- In English
- Concise
- No special characters or spaces
- No link workds like "Of", "And", "The"
- In CamelCase
- Description
- Be descriptive enough for LLM Readiness
- Use your knowledge of requirements.md file if it exists and functional project context in CONTEXT.md file
1.2 Columns
In the table paragraph, you will add : Table of columns with :
- Display Name
- Should be functional but not too long.
- Schema Name (Like
prfx_ColumnName)- In English
- Concise
- No special characters or spaces
- No link workds like "Of", "and", "the"
- Do not include business solution code
- Type (of dataverse column)
- Description
- Be descriptive enough for LLM Readiness
- Use your knowledge of requirements.md file if it exists and functional project context in CONTEXT.md file
Columns should respect good practices :
- LookUp suffixed by Id
- Choices suffixed by Code
- Boolean Prefixed by Is or Has
Important notes
- Include the Dataverse Primary Key Column: Display Name is the Table Display Name + " ID", Schema Name is the table Schema Name + "Id", Type is "GUID", Description is "Primary Key" Do not include out of the box columns such as createdon, createdby, ....
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.
- 2d ago First seen · 107 lines · 932 tokens per session scan A 0136e8fe34fd
PowerPlatform-DataverseDesign is an instructions file published in the GitHub repository tchinnin/powerplatform-vibecoding-samples (6 stars, last pushed 7mo ago), licensed MIT. It adds 932 tokens to every session, about $0.0047 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 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.