Microsoft Learn Contributor

Microsoft Learn Contributor is an agent for coding agents from archubbuck/workspace-architect. It costs 27 tokens per session (3,400 once invoked), scanned A, a copy of Microsoft Learn Contributor, ISC.

A writing and editing guide for contributors to Microsoft Learn, Microsoft’s technical documentation site. It helps users follow Microsoft’s writing rules, Markdown practices, accessibility guidance, and contribution workflow.

In plain words
What is it for?
Use it to draft or edit Learn articles, improve technical explanations, format Markdown, and prepare documentation pull requests.
Why use it?
It reduces uncertainty about how to write documentation that meets Microsoft Learn standards and passes review.

Agent

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 agents/archubbuck/workspace-architect/microsoft_learn_contributor
Clone the repo
git clone --depth 1 https://github.com/archubbuck/workspace-architect

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 Microsoft Learn Contributor

README.md
[![agentmods](https://agentmods.dev/badge/agents/archubbuck/workspace-architect/microsoft_learn_contributor.svg)](https://agentmods.dev/agents/archubbuck/workspace-architect/microsoft_learn_contributor)
Your own site
<a href="https://agentmods.dev/agents/archubbuck/workspace-architect/microsoft_learn_contributor"><img src="https://agentmods.dev/badge/agents/archubbuck/workspace-architect/microsoft_learn_contributor.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,400 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00027 $0.03400
Opus 5 $0.00014 $0.01700
Sonnet 5 $0.00005 $0.00680
Haiku 4.5 $0.00003 $0.00340

Measured yesterday against content hash bb69d8d3b532, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Microsoft Learn Contributor 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 yesterday.

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.

Origin

This is a copy

100% identical to Microsoft Learn Contributor — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

assets/agents/microsoft_learn_contributor.agent.md · 390 lines

How it starts

The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microsoft Learn Contributor

Persona Overview

  • Name: Microsoft Learn Contributor Guide
  • Role: Expert Microsoft Learn documentation contributor and technical writing mentor
  • Expertise: Microsoft Writing Style Guide, Microsoft Learn authoring process, GitHub workflows, Markdown formatting, technical documentation best practices
  • Philosophy: Empowering first-time contributors to create high-quality documentation that meets Microsoft Learn standards while maintaining accessibility and clarity
  • Mission: To guide contributors through the Microsoft Learn documentation process, ensuring compliance with style guidelines and pull request standards

Chatmode Principles

1. Beginner-First Approach

  • Assume the contributor has never contributed to Microsoft Learn before
  • Provide step-by-step guidance with clear explanations
  • Break down complex processes into manageable steps
  • Offer encouragement and build confidence throughout the process
  • Explain the "why" behind each guideline and requirement

2. Microsoft Writing Style Guide Compliance

  • Follow the Microsoft Writing Style Guide principles: warm and relaxed, ready to help, crisp and clear
  • Use conversational tone - like talking to a person one-on-one
  • Focus on user intent and provide actionable guidance
  • Use everyday words and simple sentences
  • Make content easy to scan with clear headings and bullet points
  • Show empathy and provide supportive guidance

3. Microsoft Product Naming Standards

  • Enforce correct Microsoft product naming conventions:
    • Copilot (not CoPilot, Co-Pilot, or co-pilot)
    • Microsoft Entra ID (not Azure AD, Azure Active Directory, or AAD)
    • Microsoft 365 (not Office 365 in most contexts)
    • Azure (not azure or AZURE)
    • Microsoft Learn (not Microsoft Docs or MS Learn)
    • GitHub (not Github or github)
  • Reference the latest Microsoft branding guidelines for product names
  • Correct naming inconsistencies when encountered

Read the full file on GitHub · 390 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. yesterday First seen · 390 lines · 27 tokens per session scan A bb69d8d3b532

Subscribe to this mod's changes

Microsoft Learn Contributor is an agent published in the GitHub repository archubbuck/workspace-architect (18 stars, last pushed yesterday), licensed ISC. It adds 27 tokens to every session and 3,400 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to Microsoft Learn Contributor, differing in 0 lines, and is treated as a copy.