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 skills add pinkpixel-dev/agentskills-mcp --skill project-setupgit clone --depth 1 https://github.com/pinkpixel-dev/agentskills-mcpWrote 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/pinkpixel-dev/agentskills-mcp/project-setup)<a href="https://agentmods.dev/skills/pinkpixel-dev/agentskills-mcp/project-setup"><img src="https://agentmods.dev/badge/skills/pinkpixel-dev/agentskills-mcp/project-setup/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/pinkpixel-dev/agentskills-mcp/project-setup"><img src="https://agentmods.dev/badge/skills/pinkpixel-dev/agentskills-mcp/project-setup.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 | $0.00028 | $0.01487 |
| Opus 5.5 | $0.00011 | $0.00595 |
| Sonnet 5.5 | $0.00006 | $0.00297 |
| Haiku 4.5 | $0.00003 | $0.00149 |
Grade A, and why
project-setup 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 1mo 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 — 140 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
copilot_getVSCodeAPIwith the users query to get the relevant references. - After the tool
copilot_getVSCodeAPIhas 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.
- 1mo ago First seen · 140 lines · 28 tokens per session scan A d052fbb6193d
project-setup is a skill published in the GitHub repository pinkpixel-dev/agentskills-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 1,487 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
fastmcp-client-cli
Query and invoke tools on MCP servers using fastmcp list and fastmcp call. Use when you need to discover what tools a server offers, call tools, or integrate MCP servers into workflows.
fastmcp-server
Build, extend, or review MCP servers with Python FastMCP, using documentation matched to the project's version.
code-review
Review code for quality, maintainability, and correctness.
pdf-processing
Extract text from PDFs, fill forms, and merge documents.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
create-tech-design
Only use when the user explicitly invokes this skill by name.