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/launchnpx skills add microsoft/vscode --skill launchgit clone --depth 1 https://github.com/microsoft/vscodeWhat 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 | $0.00096 | $0.07771 |
| Opus 5 | $0.00048 | $0.03886 |
| Sonnet 5 | $0.00019 | $0.01554 |
| Haiku 4.5 | $0.00010 | $0.00777 |
Grade C, and why
launch scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$(dirname "$LOG")" How it starts
The opening of the file, as written. The whole thing — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code OSS Dev - Launch + Debug
You're working on VS Code itself and you want to:
- Launch a Code OSS build from sources that is already signed in (Copilot, GitHub, etc.) so chat / agent flows work end-to-end.
- Drive it with
@playwright/cliover CDP (UI automation). - Optionally attach a debugger via dap-cli to set breakpoints in the renderer, extension host, or main process.
- Run multiple instances at once without port conflicts.
This skill provides a launcher that clones an authenticated user-data-dir to a throwaway temp folder, picks free ports for every debug surface, and prints them as JSON so you can pick them up programmatically.
The clone is slim: workspace storage, browser caches, file history, cached VSIX backups, and old logs are excluded by default. On macOS, auth tokens live in the OS keychain plus small files inside User/globalStorage - both of which are preserved. On Windows the GitHub session lives in the shared-data-dir instead, which the launcher seeds separately (see Windows authentication).
Prerequisites
- macOS, Linux, or Windows.
- macOS / Linux: the launcher is a bash script (
scripts/launch.sh) and depends onrsync,nohup, and Node onPATH. The example caller snippets below also usejq(parse the JSON output) andlsof(kill-by-port fallback) — install those if you plan to use them, but the launcher itself does not require them. - Windows: use
scripts\launch.ps1instead. It needs no extra tooling beyond Node onPATH, and works on both Windows PowerShell 5.1 and PowerShell 7+.jqis not needed — parse the JSON withConvertFrom-Json. If Node is managed with fnm, put it onPATHfirst:fnm env --use-on-cd --shell powershell | Out-String | Invoke-Expression fnm use # picks up the repo's .nvmrc
- macOS / Linux: the launcher is a bash script (
- A VS Code checkout with
node_modules/installed (npm installif missing — do not symlink from a sibling worktree; that breaks builds in subtle ways). - A VS Code checkout with sources built. Run
npm run compileonce (one-shot) ornpm run watchfor incremental rebuilds. Both build the full client and all built-in extensions underextensions/. You must build the full product to run successfully, building just the client is not enough. - An authenticated Code OSS profile to seed from. By default the launcher uses
~/.vscode-oss-devon macOS/Linux or$env:USERPROFILE\.vscode-oss-devon Windows, which is the user-data-dir the repo'slaunch.jsonconfigs use - if the user has ever signed in to Copilot in a dev build, this should work. Only pass--source-user-data-dir <path>(or set$CODE_OSS_DEV_AUTHED_USER_DATA_DIR) when you specifically want to seed from a different profile (e.g. your regular~/Library/Application Support/Codeinstall).- If Code OSS launches and needs a sign-in, don't give up! Use the questions tool to ask the user to sign in.
@playwright/cliavailable (it's a devDependency in the vscode repo -npm installthen usenpx @playwright/cli).- For debugger work:
dap-clionPATH. If debugger support would be useful but thedap-cliskill is not present, prompt the user to install it from https://github.com/roblourens/dap-cli. - CSS selectors are internal implementation details. If a selector-based
evalstops working, take a freshsnapshot, inspect the current DOM, and update the selector rather than assuming an old one still applies.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 443 lines · 96 tokens per session scan C d37ce8db747c
launch is a skill published in the GitHub repository microsoft/vscode (190,061 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 7,771 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
docx
使用 OpenXML SDK (.NET) 进行专业的 DOCX 文档创建、编辑和格式化。 三种管道:(A) 从零创建新文档,(B) 在已有文档中填充/编辑内容, (C) 应用模板格式化并通过 XSD 验证门控检查。 当用户需要生成、修改或格式化 Word 文档时,必须使用此 skill—— 包括他们说"写一份报告"、"起草建议书"、"制作合同"、 "填写此表单"、"按此模板重新排版",或任何最终输出为 .docx 文件的任务。 即使用户未明确提及 "docx",如果任务暗示生成可打印/正式文档,也应使用此 skill。.
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。.
as-planning-and-task-breakdown
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
as-spec-driven-development
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.
ecc-code-tour
Create CodeTour .tour files — persona-targeted, step-by-step walkthroughs with real file and line anchors. Use for onboarding tours, architecture walkthroughs, PR tours, RCA tours, and structured "explain how this works" requests.
ecc-codebase-onboarding
Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md. Use when joining a new project or setting up Claude Code for the first time in a repo.