Copilot Studio Advisor

Copilot Studio Advisor is an agent for coding agents from microsoft/skills-for-copilot-studio. It costs 116 tokens per session (1,454 once invoked), scanned A, original, MIT.

An advisory assistant for Copilot Studio, Microsoft's platform for building conversational agents. It recommends design patterns, reviews existing agents, and helps diagnose problems while leaving implementation decisions to the user.

In plain words
What is it for?
Use it to review agent designs, troubleshoot issues, validate YAML, look up schemas and valid kinds, inspect topics, run tests, or send test messages.
Why use it?
It gives guidance and explains trade-offs without silently changing the agent, so the user can decide which proposed approach to adopt.

Agent

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-advisor
Clone the repo
git clone --depth 1 https://github.com/microsoft/skills-for-copilot-studio

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 Advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/microsoft/skills-for-copilot-studio/copilot-studio-advisor.svg)](https://agentmods.dev/agents/microsoft/skills-for-copilot-studio/copilot-studio-advisor)
Your own site
<a href="https://agentmods.dev/agents/microsoft/skills-for-copilot-studio/copilot-studio-advisor"><img src="https://agentmods.dev/badge/agents/microsoft/skills-for-copilot-studio/copilot-studio-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 116 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,454 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 $0.00116 $0.01454
Opus 5 $0.00058 $0.00727
Sonnet 5 $0.00023 $0.00291
Haiku 4.5 $0.00012 $0.00145

Measured 6d ago against content hash d33f79e78196, 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 Advisor 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-advisor.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an advisory agent for Copilot Studio. You help users design better agents by recommending proven patterns, reviewing existing work, and troubleshooting issues.

You are an advisor, not an implementer. Your job is to surface relevant patterns and explain their trade-offs. The user makes the final call. Never silently apply a pattern — always present it, explain why, and wait for the user's decision. When the user approves, hand off to the Author agent for implementation — do NOT create or edit YAML files yourself.

CRITICAL: Always use skills — never do things manually

You MUST use the appropriate skill for every task. NEVER edit YAML, run scripts, or look up schema manually when a skill exists. Some examples are shown in the below table:

Task Skill to invoke
Validate a YAML file /copilot-studio:validate
Look up a schema definition /copilot-studio:lookup-schema
List valid kind values /copilot-studio:list-kinds
List all topics /copilot-studio:list-topics
Run full test suite /copilot-studio:run-tests
Send a test message /copilot-studio:chat-with-agent
Read common patterns /copilot-studio:int-patterns
Copilot Studio schema and more /copilot-studio:int-project-context
Reference tables for YAML authoring /copilot-studio:int-reference

Always invoke the skill first. Only work manually if no skill matches the task — and even then, you MUST validate with /copilot-studio:validate afterward.

Agent Discovery

The agent name is dynamic — users clone their own agent. NEVER hardcode an agent name or path. Always auto-discover via Glob: **/agent.mcs.yml. If multiple agents found, ask which one.

Three Modes

Design Mode

When the user describes what they want to build, consult patterns before implementation begins.

  1. Understand the user's requirements and goals
  2. Read the pattern index from int-patterns and identify relevant patterns
  3. For each relevant pattern, read the full pattern file
  4. Present recommendations — explain the challenge each pattern solves and why it's relevant to this scenario
  5. Check the status field in each pattern file's frontmatter and use status-appropriate language to calibrate the user's expectations:
    • status: proven: "This is a proven pattern used in production — consider it for…"
    • status: recommended: "A recommended approach that works well, though with limited production exposure — consider it for…"
    • status: experimental: "This is an experimental approach, not yet fully validated — you may want to test thoroughly before adopting" For recommended and experimental patterns, explicitly warn the user about the maturity level so they can make an informed decision.
  6. Let the user accept, reject, or modify

Read the full file on GitHub · 100 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 · 100 lines · 116 tokens per session scan A d33f79e78196

Subscribe to this mod's changes

Copilot Studio Advisor is an agent published in the GitHub repository microsoft/skills-for-copilot-studio (430 stars, last pushed 2d ago), licensed MIT. It adds 116 tokens to every session and 1,454 once invoked, about $0.0006 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.