microsoft/Build26-BRK242-turn-your-agents-into-action-connect-tools-apis-and-documents contains Microsoft Build 2026 session resources about connecting AI agents to tools, APIs, and documents through governed tool selection. It is intended for developers building agents that need efficient access to MCP servers, A2A, OpenAPI, connectors, built-in tools, and structured content from multimodal files. The catalogue add-ons are session instructions for exploring these agent-building patterns.
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 skills add microsoft/Build26-BRK242-turn-your-agents-into-action-connect-tools-apis-and-documents --skill knowledge-retrievalgit clone --depth 1 https://github.com/microsoft/Build26-BRK242-turn-your-agents-into-action-connect-tools-apis-and-documentsWrote 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/skills/microsoft/build26-brk242-turn-your-agents-into-action-connect-tools-apis-and-documents/knowledge-retrieval)<a href="https://agentmods.dev/skills/microsoft/build26-brk242-turn-your-agents-into-action-connect-tools-apis-and-documents/knowledge-retrieval"><img src="https://agentmods.dev/badge/skills/microsoft/build26-brk242-turn-your-agents-into-action-connect-tools-apis-and-documents/knowledge-retrieval/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/build26-brk242-turn-your-agents-into-action-connect-tools-apis-and-documents/knowledge-retrieval"><img src="https://agentmods.dev/badge/skills/microsoft/build26-brk242-turn-your-agents-into-action-connect-tools-apis-and-documents/knowledge-retrieval.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00055 | $0.01661 |
| Opus 5 | $0.00028 | $0.00830 |
| Sonnet 5 | $0.00011 | $0.00332 |
| Haiku 4.5 | $0.00006 | $0.00166 |
Grade A, and why
knowledge-retrieval 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 13d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Retrieval
Use this skill when the technician asks about procedures, safety, specifications, troubleshooting, or any technical guidance from the field operations knowledge base.
When to Use
- "How do I perform a fusion splice?"
- "What are the safety protocols for aerial work?"
- "Troubleshoot high loss on an OTDR trace"
- "What's the bend radius for single-mode fiber?"
- "What are the installation standards for underground cable?"
- "Compare single-mode vs multi-mode fiber"
Knowledge Base Contents
The knowledge base contains 8 reference documents:
- Fiber Splicing Procedures — fusion and mechanical splice techniques, preparation, verification
- Safety Protocols — PPE, aerial work, confined spaces, electrical, emergency procedures
- OTDR Testing Guide — setup, trace interpretation, acceptance thresholds, troubleshooting
- Cable Types Reference — single-mode, multi-mode, specs, applications, bend radius
- Equipment Specifications — splicers, OTDR units, cleavers, tools, calibration
- Installation Standards — underground, aerial, indoor, conduit, pull tension, routing
- Network Architecture — PON, point-to-point, FTTx, distribution, topology
- Troubleshooting Guide — loss, reflectance, breaks, macro-bends, connector issues
Tools Used by This Skill
This skill calls the knowledge_base tool (Foundry-managed Azure AI Search, no prefix).
- Tool name:
knowledge_base - Argument shape:
{"query": "<natural-language question>"}(singlequerystring — neversearch,q, orquestion). - Discovery: if
knowledge_baseis not already visible in your tool list, runtool_search({"query": "knowledge base", "limit": 10})once. Tools returned bytool_searchstay callable for the rest of the turn.
Step-by-Step Instructions
Step 1: Search the Knowledge Base
Call knowledge_base via call_tool exactly once with a clear query derived from the technician's question.
| Question Pattern | Query to Send |
|---|---|
| How to do X | "procedure for {X}" |
| Safety for X | "safety protocols for {X}" |
| Troubleshoot X | "troubleshooting {X}" |
| Specs for X | "specifications for {X}" |
| Multi-topic | Send the full question as-is |
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.
- 13d ago First seen · 176 lines · 55 tokens per session scan A f4837ff0aa08
knowledge-retrieval is a skill published in the GitHub repository microsoft/Build26-BRK242-turn-your-agents-into-action-connect-tools-apis-and-documents (10 stars, last pushed 24d ago), licensed MIT. It adds 55 tokens to every session and 1,661 once invoked, about $0.0003 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 skills, from other repositories
teams-dev
Use this skill whenever the user mentions Microsoft Teams in a development context — whether they're building, integrating, configuring, debugging, or just asking questions. Covers bots, message extensions, embedded web apps, Adaptive Cards, dialogs, SSO, infrastructure, the Teams Developer CLI/SDK, and general Teams…
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…