int-reference

int-reference is a skill for Claude Code from microsoft/skills-for-copilot-studio. It costs 35 tokens per session (3,241 once invoked), scanned A, original, MIT.

A reference guide to Copilot Studio YAML files, triggers, actions, variables, entities, functions, and templates. Copilot Studio is Microsoft's platform for building conversational agents.

In plain words
What is it for?
Use it while writing or reviewing agent metadata, settings, topics, actions, knowledge sources, variables, child agents, triggers, and Power Fx expressions.
Why use it?
It gives you the names and purposes of the building blocks used to author an agent. It also explains how classic and generative orchestration affect topic routing.

Skill for Claude Code ✓ vendor

Written for Claude Code: user-invocable in frontmatter. Also seen: names the EndConversation tool.

Part of the copilot-studio plugin — 31 skills, 4 agents, 1 hook shipped together

Good fit Use it while writing or reviewing agent metadata, settings, topics, actions, knowledge sources, variables, child agents, triggers, and Power Fx expressions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/microsoft/skills-for-copilot-studio/int-reference
About the project

Skills for Copilot Studio is a plugin for authoring, testing, and troubleshooting standard Microsoft Copilot Studio agents as YAML files from a terminal or editor. It is intended for users of Claude Code, GitHub Copilot CLI, and VS Code who work with Copilot Studio agents. The catalogue add-ons are the plugin's skills, agents, hook, and plugin definition.

microsoft/skills-for-copilot-studio · 432 stars · on GitHub

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.

Any agent
npx skills add microsoft/skills-for-copilot-studio --skill int-reference
Clone the repo
git clone --depth 1 https://github.com/microsoft/skills-for-copilot-studio

Made for: Claude Code.

Or install copilot-studio, the plugin that ships this one along with the rest of its 31 skills, 4 agents, 1 hook.

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 int-reference

README.md
[![agentmods](https://agentmods.dev/badge/skills/microsoft/skills-for-copilot-studio/int-reference.svg)](https://agentmods.dev/skills/microsoft/skills-for-copilot-studio/int-reference)
Your own site
<a href="https://agentmods.dev/skills/microsoft/skills-for-copilot-studio/int-reference"><img src="https://agentmods.dev/badge/skills/microsoft/skills-for-copilot-studio/int-reference.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,241 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00035 $0.03241
Opus 5 $0.00017 $0.01621
Sonnet 5 $0.00007 $0.00648
Haiku 4.5 $0.00003 $0.00324

Measured 7d ago against content hash 81f7d955f2f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

int-reference 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 7d 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.

skills/int-reference/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Studio YAML Reference

Core File Types

File Purpose
agent.mcs.yml Main agent metadata (kind: GptComponentMetadata)
settings.mcs.yml Agent settings and configuration
connectionreferences.mcs.yml Connector references
topics/*.mcs.yml Conversation topics (kind: AdaptiveDialog)
actions/*.mcs.yml Connector-based actions (kind: TaskDialog)
knowledge/*.mcs.yml Knowledge sources (kind: KnowledgeSourceConfiguration)
variables/*.mcs.yml Global variables (kind: GlobalVariableComponent)
agents/*.mcs.yml Child agents (kind: AgentDialog)

Trigger Types

Topics with OnRecognizedIntent have two routing mechanisms — which one matters depends on the orchestration mode:

  • modelDescription — used by generative orchestration (GenerativeActionsEnabled: true). The AI orchestrator reads this to decide routing. Primary mechanism for generative agents.
  • Trigger phrases (triggerQueries) — used by classic orchestration. Pattern-matched against the user's utterance. Secondary hints when generative orchestration is enabled.

System triggers (OnConversationStart, OnUnknownIntent, OnError, etc.) fire automatically and don't use either mechanism.

Kind Purpose
OnRecognizedIntent Trigger phrases matched
OnConversationStart Conversation begins
OnUnknownIntent No topic matched (fallback)
OnEscalate User requests human agent
OnError Error handling
OnSystemRedirect Triggered by redirect only
OnSelectIntent Multiple topics matched (disambiguation)
OnSignIn Authentication required
OnToolSelected Child agent invocation
OnKnowledgeRequested Custom knowledge source search triggered (YAML-only, no UI)
OnGeneratedResponse Intercept AI-generated response before sending
OnOutgoingMessage Non-functional (2026-03-15) — exists in schema but does not fire at runtime. Do not use.

Read the full file on GitHub · 244 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. 7d ago First seen · 244 lines · 35 tokens per session scan A 81f7d955f2f5

Subscribe to this mod's changes

int-reference is a skill published in the GitHub repository microsoft/skills-for-copilot-studio (432 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 3,241 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens