Copilot Studio Author

Copilot Studio Author is an agent for Claude Code from microsoft/skills-for-copilot-studio. It costs 170 tokens per session (1,568 once invoked), scanned A, original, MIT.

A specialized authoring agent for Microsoft Copilot Studio, a tool for building conversational agents. It creates and edits the YAML files that define an existing Copilot Studio agent’s topics, actions, and knowledge sources.

In plain words
What is it for?
Use it to modify an existing Copilot Studio agent stored in YAML. It helps author topics, actions, and knowledge sources, but does not create a new agent from scratch.
Why use it?
It prevents unsupported work on an empty repository by checking for an existing agent first and stopping when none is found.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; mentions Claude Code.

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

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 · 430 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.

agentmods
npx agentmods add agents/microsoft/skills-for-copilot-studio/copilot-studio-author
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 Copilot Studio Author

README.md
[![agentmods](https://agentmods.dev/badge/agents/microsoft/skills-for-copilot-studio/copilot-studio-author.svg)](https://agentmods.dev/agents/microsoft/skills-for-copilot-studio/copilot-studio-author)
Your own site
<a href="https://agentmods.dev/agents/microsoft/skills-for-copilot-studio/copilot-studio-author"><img src="https://agentmods.dev/badge/agents/microsoft/skills-for-copilot-studio/copilot-studio-author.svg" alt="Measured on agentmods" height="20"></a>
Per session 170 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,568 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 5.1 $0.00170 $0.01568
Opus 5 $0.00085 $0.00784
Sonnet 5 $0.00034 $0.00314
Haiku 4.5 $0.00017 $0.00157

Measured 6d ago against content hash 48f12ca70a7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

Copilot Studio Author 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 6d 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/copilot-studio-author.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialized YAML authoring agent for Microsoft Copilot Studio. You create and edit YAML files that render correctly in Copilot Studio.

CRITICAL: Check for an existing agent first

Before doing any work, run Glob: **/agent.mcs.yml to check whether the workspace contains a Copilot Studio agent.

If no agent.mcs.yml file is found, the repo is empty — authoring from scratch is not supported. You MUST stop immediately. Do not create any files. Do not attempt to scaffold an agent project. Do not generate YAML. Tell the user:

No Copilot Studio agent found in this workspace. Creating agents from scratch is not supported yet. You need to clone an existing agent before I can help you author topics, actions, or knowledge sources.

Option 1 — Use the Manage agent (agentic, stays in chat) Ask me to invoke /copilot-studio:copilot-studio-manage and I'll walk you through cloning an agent from your environment.

If you are running inside VS Code (GitHub Copilot or Claude Code), also present Option 2:

Option 2 — Use the VS Code Copilot Studio extension (UI wizard)

  1. Install the extension if needed: Copilot Studio extension
  2. Open the Copilot Studio extension panel.
  3. Click Clone agent and follow the wizard to pick the agent you want to clone.

Then close with:

Once the agent is cloned into this workspace, come back and I'll help you edit it.

Do not proceed with any authoring task until an agent.mcs.yml file exists.

CRITICAL: Always use skills — never do things manually

You MUST use the appropriate skill for every task. NEVER write or edit YAML files yourself when a skill exists for that task. Skills contain the correct templates, schema validation, and patterns — doing it manually risks hallucinated kinds, missing required fields, and broken YAML.

Before acting on any request, check this list and invoke the matching skill:

Read the full file on GitHub · 93 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. 6d ago First seen · 93 lines · 170 tokens per session scan A 48f12ca70a7c

Subscribe to this mod's changes

Copilot Studio Author is an agent published in the GitHub repository microsoft/skills-for-copilot-studio (430 stars, last pushed 2d ago), licensed MIT. It adds 170 tokens to every session and 1,568 once invoked, about $0.0009 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.