pennant-development

pennant-development is a skill for Claude Code, Codex from laravel/boost. It costs 124 tokens per session (386 once invoked), scanned A, original, MIT.

A guide for Laravel Pennant, the official Laravel package for feature flags. Feature flags let an application turn features on or off, sometimes for selected users.

In plain words
What is it for?
Use it when adding or reviewing Laravel feature flags, including user-specific flags, class-based features, and Blade templates that show different content by flag state.
Why use it?
It provides documented patterns and checks for defining, scoping, activating, and testing Pennant flags, reducing common setup mistakes.

Skill for Claude CodeCodex

About the project

Laravel Boost is an MCP server that supplies AI coding assistants with Laravel-specific project context and structure. It is intended to support AI-assisted local Laravel development, and the catalogue entries provide skills for that workflow.

laravel/boost · 3,600 stars · on GitHub

Install

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.

agentmods
npx agentmods add skills/laravel/boost/pennant-development
Any agent
npx skills add laravel/boost --skill pennant-development
Clone the repo
git clone --depth 1 https://github.com/laravel/boost

Made for: Claude Code, Codex.

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 pennant-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/laravel/boost/pennant-development.svg)](https://agentmods.dev/skills/laravel/boost/pennant-development)
Your own site
<a href="https://agentmods.dev/skills/laravel/boost/pennant-development"><img src="https://agentmods.dev/badge/skills/laravel/boost/pennant-development.svg" alt="Measured on agentmods" height="20"></a>
Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 386 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00124 $0.00386
Opus 5 $0.00062 $0.00193
Sonnet 5 $0.00025 $0.00077
Haiku 4.5 $0.00012 $0.00039

Measured 5d ago against content hash 96addef8df94, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pennant-development 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 5d 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.

.ai/pennant/skill/pennant-development/SKILL.md · 69 lines

What it actually says

Pennant Features

Documentation

Use search-docs for detailed Pennant patterns and documentation.

Basic Usage

Defining Features

use Laravel\Pennant\Feature;

Feature::define('new-dashboard', function (User $user) {
    return $user->isAdmin();
});

Checking Features

if (Feature::active('new-dashboard')) {
    // Feature is active
}

// With scope
if (Feature::for($user)->active('new-dashboard')) {
    // Feature is active for this user
}

Blade Directive

@feature('new-dashboard')
    <x-new-dashboard />
@else
    <x-old-dashboard />
@endfeature

Activating / Deactivating

Feature::activate('new-dashboard');
Feature::for($user)->activate('new-dashboard');

Verification

  1. Check feature flag is defined
  2. Test with different scopes/users

Common Pitfalls

  • Forgetting to scope features for specific users/entities
  • Not following existing naming conventions
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. 5d ago First seen · 69 lines · 124 tokens per session scan A 96addef8df94

Subscribe to this mod's changes

pennant-development is a skill published in the GitHub repository laravel/boost (3,600 stars, last pushed 4d ago), licensed MIT. It adds 124 tokens to every session and 386 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories