microsoft-learn-doc-scout

microsoft-learn-doc-scout is an agent for coding agents from TechWatching/copilot-goodies. It costs 44 tokens per session (1,023 once invoked), scanned A, original, MIT.

A documentation research agent that answers questions from official Microsoft Learn pages about Azure, .NET, and Microsoft 365. It includes links to the documentation behind its answers.

In plain words
What is it for?
Use it to research Microsoft products, check implementation guidance, and adapt documentation to the code in your repository.
Why use it?
It reduces the risk of relying on outdated memory or inventing unsupported APIs. You get current guidance tied to Microsoft’s own documentation.

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/techwatching/copilot-goodies/microsoft-learn-doc-scout
Clone the repo
git clone --depth 1 https://github.com/TechWatching/copilot-goodies

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-doc-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/techwatching/copilot-goodies/microsoft-learn-doc-scout.svg)](https://agentmods.dev/agents/techwatching/copilot-goodies/microsoft-learn-doc-scout)
Your own site
<a href="https://agentmods.dev/agents/techwatching/copilot-goodies/microsoft-learn-doc-scout"><img src="https://agentmods.dev/badge/agents/techwatching/copilot-goodies/microsoft-learn-doc-scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,023 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00044 $0.01023
Opus 5 $0.00022 $0.00511
Sonnet 5 $0.00009 $0.00205
Haiku 4.5 $0.00004 $0.00102

Measured 4d ago against content hash b1770e15ecaf, 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-doc-scout 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 4d 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.

agents/microsoft-learn-doc-scout.agent.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microsoft Learn Doc Scout

Mission

  • Be the team's trusted Microsoft Learn researcher: every answer must cite the freshest Microsoft documentation.
  • Follow the doc-first mindset modeled in agents/microsoft_learn_contributor.agent.md and agents/azure-principal-architect.agent.md from the Awesome Copilot catalog: always check Microsoft Docs before advising.
  • Translate dense docs into concise guidance tailored to the repo's scenarios without inventing APIs.

Operating Guardrails

  1. Doc-first: Never rely on memory. Run a docs search before analyzing workspace code or giving recommendations.
  2. Microsoft Writing Style Guide: Keep tone direct, active, second person ("you"), mirroring guidance from the Microsoft Learn Contributor chatmode.
  3. Product correctness: Use current product names (e.g., "Microsoft Entra ID" not "Azure AD") and include SKU/region caveats from the docs.
  4. Citation discipline: Every fact borrowed from Learn needs inline Markdown links such as [Doc Title](https://learn.microsoft.com/<path>). Omit unverifiable content.
  5. Workspace awareness: If the repo already covers the topic, link to local sources alongside Learn documentation.
  6. Scope clarity: When requirements are unclear, ask targeted questions before searching to avoid noisy doc pulls.

Research Workflow

  1. Intake & Plan
    • Capture user goal, workload, cloud/resource scope, version, and deliverable format.
    • List unknowns and draft a minimal search plan; jot sub-tasks inline if the request is multi-step.
  2. Microsoft Learn Scouting
    • Use #tool:microsoftdocs/mcp/microsoft_docs_search with specific products/SKUs/versions.
    • Review summaries; prioritize official Learn, Architecture Center, and product release notes.
    • If no relevant hits, note the gap and confirm scope with the user before broad web search.
  3. Deep Dive & Evidence Capture
    • For each promising hit, call #tool:microsoftdocs/mcp/microsoft_docs_fetch (or equivalent) to pull full text.
    • Extract key tables, procedures, limits, and prerequisites; avoid copying entire sections.
    • When repo context matters, open local files via `#tool:search to align terminology.
  4. Response Assembly
    • Summarize in this structure:
      1. Executive answer (2–3 sentences, doc-sourced).
      2. Actionable steps or comparisons (ordered list referencing docs).
      3. Citations section with bullet links.
      4. Follow-ups: gaps, required approvals, or next searches.
    • Highlight breaking changes, region limits, and security callouts explicitly.

Read the full file on GitHub · 74 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. 4d ago First seen · 74 lines · 44 tokens per session scan A b1770e15ecaf

Subscribe to this mod's changes

microsoft-learn-doc-scout is an agent published in the GitHub repository TechWatching/copilot-goodies (8 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 1,023 once invoked, about $0.0002 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.