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/project-setup-info-localnpx skills add microsoft/vscode --skill project-setup-info-localgit 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/project-setup-info-local)<a href="https://agentmods.dev/skills/microsoft/vscode/project-setup-info-local"><img src="https://agentmods.dev/badge/skills/microsoft/vscode/project-setup-info-local.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 | $0.00263 | $0.01700 |
| Opus 5 | $0.00131 | $0.00850 |
| Sonnet 5 | $0.00053 | $0.00340 |
| Haiku 4.5 | $0.00026 | $0.00170 |
Grade A, and why
project-setup-info-local 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- project-setup-info-local — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
How to setup a project
Determine what kind of project the user wants to create, then based on that, choose which setup info below to follow. Only setup a project if the folder is empty or if you've just called the tool first calling the tool to create a workspace.
vscode-extension
A template for creating a VS Code extension using Yeoman and Generator-Code.
Run this command:
npx --package yo --package generator-code -- yo code . --skipOpen
The command has the following arguments:
-t, --extensionType: Specify extension type: ts, js, command-ts, command-js, colortheme, language, snippets, keymap, extensionpack, localization, commandweb, notebook. Defaults tots-n, --extensionDisplayName: Set the display name of the extension.--extensionId: Set the unique ID of the extension. Do not select this option if the user has not requested a unique ID.--extensionDescription: Provide a description for the extension.--pkgManager: Specify package manager: npm, yarn, or pnpm. Defaults tonpm.--bundler: Bundle the extension using webpack or esbuild.--gitInit: Initialize a Git repository for the extension.--snippetFolder: Specify the location of the snippet folder.--snippetLanguage: Set the language for snippets.
Rules
- Do not remove any arguments from the command. Only add arguments if the user requests them.
- Call the tool
get_vscode_apiwith the user's query to get the relevant references. - After the tool
get_vscode_apihas completed, only then begin to modify the project.
next-js
A React based framework for building server-rendered web applications.
Run this command:
npx create-next-app@latest .
The command has the following arguments:
--ts, --typescript: Initialize as a TypeScript project. This is the default.--js, --javascript: Initialize as a JavaScript project.--tailwind: Initialize with Tailwind CSS config. This is the default.--eslint: Initialize with ESLint config.--app: Initialize as an App Router project.--src-dir: Initialize inside a 'src/' directory.--turbopack: Enable Turbopack by default for development.--import-alias <prefix/*>: Specify import alias to use.(default is "@/*")--api: Initialize a headless API using the App Router.--empty: Initialize an empty project.--use-npm: Explicitly tell the CLI to bootstrap the application using npm.--use-pnpm: Explicitly tell the CLI to bootstrap the application using pnpm.--use-yarn: Explicitly tell the CLI to bootstrap the application using Yarn.--use-bun: Explicitly tell the CLI to bootstrap the application using Bun.
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 · 128 lines · 263 tokens per session scan A 6205fdc9201e
project-setup-info-local is a skill published in the GitHub repository microsoft/vscode (190,863 stars, last pushed today), licensed MIT. It adds 263 tokens to every session and 1,700 once invoked, about $0.0013 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
cyrene-plan-mode
当 Cyrene 处于 Plan Mode（计划模式），正在讨论、调查、细化或准备代码/文件改动的实施计划时使用。.
cyrene-plugin-dev
当用户想为 Cyrene 开发插件（扩展昔涟的工具、做插件弹窗、接入渠道）、调试插件报错，或询问插件怎么写时使用。涉及 Cyrene 本体源码的功能开发不使用本 Skill。.
cyrene-work-hygiene
在 Work 模式中创建、整理或交付多文件工作成果时使用：先理解已有工作区，再选择最小且清晰的目录结构；普通问答、只读分析和单文件小修改不使用。.
cyrene-obsidian-workspace
Cyrene 在 Learn 模式下操作 Obsidian Vault 的规范：目录约定、文件读取、按标题定位、创建与修改 Markdown 的安全原则。.
cyrene-learn-tutor
Cyrene 在 Learn 模式下的教学流程策略：陪伴用户理解材料、生成练习、检查理解、维护学习进度。.
cyrene-original-voice
昔涟原作语气校准。系统自动检测场景并强制注入语气规则到 system prompt，ILM 必须遵守，不可选择忽略。.