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 agentmods add skills/pnp/copilot-pro-dev-samples/copilot-studio-sample-reviewnpx skills add pnp/copilot-pro-dev-samples --skill copilot-studio-sample-reviewgit clone --depth 1 https://github.com/pnp/copilot-pro-dev-samplesWrote 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/pnp/copilot-pro-dev-samples/copilot-studio-sample-review)<a href="https://agentmods.dev/skills/pnp/copilot-pro-dev-samples/copilot-studio-sample-review"><img src="https://agentmods.dev/badge/skills/pnp/copilot-pro-dev-samples/copilot-studio-sample-review.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.00643 |
| Opus 5 | $0.00016 | $0.00321 |
| Sonnet 5 | $0.00007 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
copilot-studio-sample-review 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Studio Sample Review
Review Copilot Studio sample PRs (folders starting with mcs-) for compliance with repo guidelines.
Use when a request asks to review an mcs-* sample PR (e.g., "review PR" or "review this sample").
Workflow
- Checkout PR:
gh pr checkout <number> - Verify sample folder starts with
mcs- - Run checks below, collecting comments (file, line, issue)
- Submit all comments in single API call (GitHub limitation)
Checks
1. Folder and file structure
- Sample is under
samples/mcs-* - Required top-level files/folders are present:
README.md,assets/,src/ assets/sample.jsonexists and includes correct sample folder references
2. No packaged exports
- Request changes if any packaged
.zipexports are committed undersamples/mcs-*(e.g.,samples/mcs-example/export.zip). Extracted source files are required, whether the contributor usedpac solution cloneor the VS Code clone method. - Copilot Studio exports must be committed as extracted source files only
3. README and template alignment
- README is based on
/templates/mcs-copilot-studio/README.md - Setup steps include one of the supported contributor flows:
- Solution export via Power Platform CLI (
pac solution clone) - Copilot Studio Visual Studio Code clone method
- Solution export via Power Platform CLI (
4. Metadata consistency
assets/sample.jsonnameusespnp-copilot-pro-dev-<sample-folder>urlanddownloadUrltarget the correctsamples/mcs-*path- Author information and thumbnail paths match repository conventions
Submitting Reviews
GitHub API does not support adding comments to a review after it has been created. Collect all comments first and submit them in one API call.
Get commit SHA:
gh pr view <PR> --json headRefOid
Create review.json:
{
"commit_id": "<sha>",
"event": "<REQUEST_CHANGES|COMMENT|APPROVE>",
"body": "Summary message",
"comments": [
{"path": "file/path", "line": 10, "body": "Issue description"}
]
}
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.
- 4d ago First seen · 75 lines · 33 tokens per session scan A 3b017417098c
copilot-studio-sample-review is a skill published in the GitHub repository pnp/copilot-pro-dev-samples (156 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 643 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.
Other skills, from other repositories
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
verify
Use when you want to validate changes before committing, or when you need to check all React contribution requirements.
ast-grep
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for…
run-integration-tests
Build, pack, and run .NET MAUI integration tests locally. Validates templates, samples, and end-to-end scenarios using the local workload.
run-helix-tests
Submit and monitor .NET MAUI unit tests on Helix infrastructure. Supports running XAML, Resizetizer, Core, Essentials, and other unit test projects on distributed Helix queues.
extract-errors
Use when adding new error messages to React, or seeing "unknown error code" warnings.