Visual Studio Code is a code editor that supports editing, navigating, understanding, debugging, and extending software projects. Developers use it for the edit-build-debug cycle, and the catalogue add-ons provide skills, instructions, and agents for working within the editor.
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/microsoft/vscode/github-copilot-upgradernpx skills add microsoft/vscode --skill github-copilot-upgradergit clone --depth 1 https://github.com/microsoft/vscodeWrote 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/vscode/github-copilot-upgrader)<a href="https://agentmods.dev/skills/microsoft/vscode/github-copilot-upgrader"><img src="https://agentmods.dev/badge/skills/microsoft/vscode/github-copilot-upgrader.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 | $0.00018 | $0.00758 |
| Opus 5 | $0.00009 | $0.00379 |
| Sonnet 5 | $0.00004 | $0.00152 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
github-copilot-upgrader 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 yesterday.
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.
You are an expert at upgrading the @github/copilot npm package in the vscode-copilot-chat project.
Upgrade Process
You must create a TODO list of all items that are to be completed. You MUST create a TODO markdown file before commencing any of the work. Update this file after each step is completed. Complete all TODO items in sequence without stopping to ask for confirmation, only stop if you encounter any ambiguous decision that requires user input. The TODO is your primary tracking mechanism. Before each step you MUST read the TODO to determine what to do next.
At a minimum your TODO must contain the following:
- Snapshot old type definitions
- Update the package
- Compare differences in type definitions and document them
- Compile,
- fix
- test
- Repease steps Compile, fix and tests until all tests are passing
- Run integration tests
- Repeate Compile, Fix, Test, until all tests are passing
- Create a summary
Note:
- Do not run any integration test.
Follow these steps exactly:
1. Snapshot of old type definitions
Take a snapshot of node_modules/@github/copilot/sdk/index.d.ts to compare against after the upghttps://github.com/microsoft/vscode/issues/291457rade.
2. Update the package using command npm install @github/copilot@latest
After this you MSUT run npm run postinstall
3. Compare differences in type definitions
- Use mode=background for comparing the files and when done, just let me know its done
- This is what you need to do in the background task:
- Analyze the differences between the old and new index.d.ts files to identify any API changes, new features, or breaking changes.
- Document the changes in a clear and organized manner, create the documentation in in .build/upgrade-notes.md
4. Compile, fix and test
4.1 Compile
- Run the following commands to identify any type errors caused by the upgrade:
- You must perform a deep analysis of the compilation errors before attempting to resolve them.
- Ensure there are no compilation errors before proceeding to run the tests.
npm run postinstall
npm run compile
npx tsc --noEmit --project tsconfig.json
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.
- yesterday First seen · 75 lines · 18 tokens per session scan A d90ac0655cae
github-copilot-upgrader is a skill published in the GitHub repository microsoft/vscode (190,808 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 758 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
evaluate-pr-tests
Evaluates tests added in a PR for coverage, quality, edge cases, and test type appropriateness. Checks if tests cover the fix, finds gaps, and recommends lighter test types when possible. Prefer unit tests over device tests over UI tests. Triggers on: 'evaluate tests in PR', 'review test quality', 'are these tests…
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.
write-xaml-tests
Creates XAML unit tests for GitHub issues in the Controls.Xaml.UnitTests project. Tests XAML parsing, compilation (XamlC), and source generation. Use when testing XAML-specific behavior, not UI interactions.
author-test
Generate a test given sample. Parameters: C# SDK repository root; Package name: one of Azure.AI.Projects, Azure.AI.Projects.Agents or Azure.AI.Extensions.OpenAI; the sample to use as a starting point for the test.
precommit
Pre-commit checks — lint:fix -> build -> test.
precommit-fast
Quick pre-commit checks — lint:fix -> test.