init

init is a command for Claude Code from gopherguides/gopher-ai. It costs 10 tokens per session (4,204 once invoked), scanned A, original, MIT.

A command that sets up Tailwind CSS v4 in an existing project. Tailwind CSS is a web-styling system that uses reusable classes to build page designs.

In plain words
What is it for?
Use it to initialize Tailwind in the current project or in a specified project directory.
Why use it?
It handles project detection, dependency installation, CSS setup, and build integration instead of requiring each step by hand.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the tailwind plugin — 5 skills, 4 commands shipped together

Good fit Use it to initialize Tailwind in the current project or in a specified project directory.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add gopherguides/gopher-ai
Claude Code
/plugin install tailwind

Made for: Claude Code.

Or install tailwind, the plugin that ships this one along with the rest of its 5 skills, 4 commands.

Wrote 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.

agentmods badge for init

README.md
[![agentmods](https://agentmods.dev/badge/commands/gopherguides/gopher-ai/init/github.svg)](https://agentmods.dev/commands/gopherguides/gopher-ai/init)
Your own site
<a href="https://agentmods.dev/commands/gopherguides/gopher-ai/init"><img src="https://agentmods.dev/badge/commands/gopherguides/gopher-ai/init/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.

agentmods 80×15 button for init

Your own site · 80×15
<a href="https://agentmods.dev/commands/gopherguides/gopher-ai/init"><img src="https://agentmods.dev/badge/commands/gopherguides/gopher-ai/init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,204 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00010 $0.04204
Opus 5.5 $0.00004 $0.01682
Sonnet 5.5 $0.00002 $0.00841
Haiku 4.5 $0.00001 $0.00420

Measured 1mo ago against content hash c1d28bc52ced, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

init 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.

plugins/tailwind/commands/init.md · 440 lines

How it starts

The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Initialize Tailwind CSS v4

If $ARGUMENTS is empty or not provided:

Initialize Tailwind CSS v4 in the current directory.

Usage: /tailwind-init [project-path]. /tailwind-init (current dir) or /tailwind-init ./my-app (specific dir).

What it does: detect project type → check for existing Tailwind → choose integration method → install deps → create CSS entry file with v4 syntax → configure the selected build integration.

v4 key changes: no tailwind.config.js (configure in CSS via @theme); single @import "tailwindcss";; auto-detects templates (@source only for custom paths).

Proceed after binding the current directory as the initialization operation root described below.


If $ARGUMENTS is provided:

Initialize Tailwind CSS v4 in: $ARGUMENTS.

Initialization Operation Root

Parse at most one positional project path from the invocation arguments. Bind the requested project path to <INIT_TARGET> as one concrete normalized absolute directory. When no path was provided, bind the invocation's current directory. Stop before any mutation when the path does not exist, is not a directory, or extra positional arguments remain. Bind <INIT_TARGET> once and do not re-derive or broaden it later.

Treat <INIT_TARGET> as the application and integration mutation scope for the entire workflow. Execute application discovery, file edits, integration configuration, and direct tool validation with <INIT_TARGET> as the working directory. Resolve every application path, including the member package.json, CSS entries, build configuration, and .gitignore, against <INIT_TARGET>. The only permitted ancestor discovery and mutation are the read-only package-ownership search and owning lockfile update described under Package Manager Selection. Do not treat the package root as a broader application mutation scope, and do not inspect or change the invocation directory unless it is <INIT_TARGET> or the owning package root.

Loop Initialization

Read the full file on GitHub · 440 lines

Changes

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.

  1. 1mo ago Changed c1d28bc52ced
  2. 1mo ago First seen · 440 lines · 10 tokens per session scan A 92d0c3078803

Subscribe to this mod's changes

init is a command published in the GitHub repository gopherguides/gopher-ai (21 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 4,204 once invoked, about $0.0000 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 2026-09-03.