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.
Borrowing it
Nothing to install: this file belongs to microsoft/vscode. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/vscode/main/.github/skills/feature-tryouts/SKILL.mdgit 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/feature-tryouts)<a href="https://agentmods.dev/skills/microsoft/vscode/feature-tryouts"><img src="https://agentmods.dev/badge/skills/microsoft/vscode/feature-tryouts/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/vscode/feature-tryouts"><img src="https://agentmods.dev/badge/skills/microsoft/vscode/feature-tryouts.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00047 | $0.02342 |
| Opus 5.5 | $0.00019 | $0.00937 |
| Sonnet 5.5 | $0.00009 | $0.00468 |
| Haiku 4.5 | $0.00005 | $0.00234 |
Grade A, and why
feature-tryouts 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 15d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature tryouts
Feature tryouts connect release-note links to trusted product interactions. Use this skill to choose the least invasive useful experience, keep behavior feature-owned, bind guidance to the correct UI instance, fail closed, and validate the real journey.
The authoritative contributor contract is src/vs/workbench/contrib/onboarding/README.md. Read it before implementation. This skill owns the execution workflow and must not duplicate a catalogue of current tryouts.
1. Classify the experience
Choose the least invasive level that provides value:
| Level | Use when |
|---|---|
| Try it | Behavior can be prepared safely with isolated data |
| Guide me | Opening and highlighting a real control is sufficient |
| Help me get ready | The user must perform a prerequisite |
| Use my context | The action must bind to an exact editor, session, or widget |
| Explain only | Interaction would be unsafe, misleading, or impossible |
A spotlight alone can be useful. A tryout does not need to reproduce the complete feature.
2. Establish ownership and side effects
Before editing, answer:
- What useful state should the user reach?
- Which component owns that behavior?
- What may the tryout change?
- What must remain an explicit user action?
- What prerequisites can be missing?
- Can several matching controls be visible?
- Does preparation need an exact editor, session, or widget?
- Does execution cross into the Agents window?
- Is this an AI feature subject to Chat, provider, model, workspace, or managed-policy gates?
- How will cancellation suppress late asynchronous effects?
Prefer feature-owned contributions and commands. Shared onboarding code should provide reusable lifecycle and presentation primitives, not feature policy.
3. Choose a presentation
| Need | Presentation |
|---|---|
| Run an existing product command with installed-code arguments | command |
| Open a contributed view or view container | openView |
| Show deterministic, read-only text or a comparison | editorSample |
| Prepare an exact feature-owned UI instance | Feature-owned launch presentation |
| Launch a surface and guide one or more controls | Guided presentation |
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.
- 15d ago Changed f77405efb814
- 21d ago First seen · 239 lines · 47 tokens per session scan A 40457a952588
feature-tryouts is a skill published in the GitHub repository microsoft/vscode (193,657 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 2,342 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-25.
Other skills, from other repositories
cyrene-plan-mode
A planning guide for Cyrene’s Plan Mode, used before code or file changes are made. It helps turn a broad request into an agreed implementation plan based on the project’s actual code and constraints.
cyrene-plugin-dev
A guide for developing runtime plugins for Cyrene, including plugins that add tools, windows, events, live context, or connections to services. Cyrene is the host application that runs these plugins.
cyrene-exam-paper
A method for creating formal exams from a learning plan, then keeping the questions, answers, grading, and review separate. It maps learned topics to skills and suitable question types.
cyrene-obsidian-workspace
A set of rules for an agent working with an Obsidian vault, a folder of linked Markdown notes. It defines where materials, notes, exercises, templates, and progress files belong and how they may be edited.
cyrene-work-hygiene
A Work-mode rulebook for organizing projects that create, arrange, or deliver several files.
cyrene-diagram
A design guide for making static SVG learning cards: small diagrams or reference cards rendered as images. It explains when to use a card instead of Mermaid, a text-based diagram format, and sets layout, color, size, and safety rules.