package-skeleton: Skill for Claude Code

.agents/skills/package-generate-skill/SKILL.md

package-generate-skill is a skill for Claude Code, Codex from laravel/package-skeleton. It costs 55 tokens per session (615 once invoked), scanned A, original, MIT.

A maintenance guide for the Laravel Boost skill bundled with a Laravel package. Laravel is a PHP framework for building web applications, and Boost is its package-adoption guidance.

In plain words
What is it for?
Use it after changing a package's public integration points to update and check its bundled Boost skill, examples, references, and anti-patterns.
Why use it?
It helps keep the bundled instructions accurate when a package's public commands, settings, routes, views, or documentation change.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is laravel/package-skeleton's own configuration. It tells Claude Code and Codex how to work on package-skeleton itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything package-skeleton configures →

About the project

Laravel Package Skeleton is a starter repository for creating Laravel packages, with package configuration, testing, static analysis, formatting, and a workbench application already set up. Laravel package developers use it as the starting point for new packages. The catalogue add-ons support workflows around this package template.

laravel/package-skeleton · 60 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to laravel/package-skeleton. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/laravel/package-skeleton/main/.agents/skills/package-generate-skill/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/laravel/package-skeleton

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 package-generate-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/laravel/package-skeleton/package-generate-skill.svg)](https://agentmods.dev/skills/laravel/package-skeleton/package-generate-skill)
Your own site
<a href="https://agentmods.dev/skills/laravel/package-skeleton/package-generate-skill"><img src="https://agentmods.dev/badge/skills/laravel/package-skeleton/package-generate-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 615 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 52
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00055 $0.00615
Opus 5 $0.00028 $0.00308
Sonnet 5 $0.00011 $0.00123
Haiku 4.5 $0.00006 $0.00061

Measured 8d ago against content hash 2d2993c2a5ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

package-generate-skill 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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/package-generate-skill/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Package Generate Skill

Primary Goal

Keep the package's bundled Boost skill accurate, concise, and focused on helping Laravel applications adopt the package.

Workflow

  1. Inspect the package implementation before editing the Boost skill: service provider, facades, public classes, commands, config, routes, migrations, events, views, publish tags, and tests.
  2. Inspect package documentation: README.md, contributing docs, examples, and changelog entries that describe user-facing behavior.
  3. Identify the public integration surface only. Include install, configure, publish, command, route, facade, helper, middleware, event, and testing guidance only when the package actually exposes it.
  4. Update resources/boost/skills/*/SKILL.md with practical adoption steps, references, examples, and anti-patterns for Laravel app developers using the package.
  5. Preserve front matter, package metadata, and the Boost skill structure: description, primary goal, workflow, references, examples, and anti-patterns.
  6. Validate that the Boost skill does not describe internals as public API and does not document features that are not implemented.

Writing Rules

  • Write for consumers installing the package in a Laravel application, not for maintainers changing package internals.
  • Prefer short, task-oriented steps over broad explanations.
  • Point to concrete files only when they help the consumer understand package adoption.
  • Keep examples runnable and aligned with documented package names, config keys, commands, and publish tags.
  • Keep the skill small enough for an agent to load and apply quickly.

References

  • resources/boost/skills/
  • src/*ServiceProvider.php
  • src/Facades/
  • src/Console/Commands/
  • config/*.php
  • routes/*.php
  • database/migrations/
  • README.md
  • tests/Feature/ and tests/Unit/

Examples

  • After adding a new Artisan command, update the Boost skill with when to run it, required options, expected output, and any related config.
  • After adding config and publish tags, update the Boost skill with publish commands and the minimum config keys users need to set.
  • After adding a facade or public class, update the Boost skill with one practical integration example and the test assertion a consuming app should use.

Read the full file on GitHub · 56 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. 8d ago First seen · 56 lines · 55 tokens per session scan A 2d2993c2a5ca

Subscribe to this mod's changes

package-generate-skill is a skill published in the GitHub repository laravel/package-skeleton (60 stars, last pushed 5d ago), licensed MIT. It adds 55 tokens to every session and 615 once invoked, about $0.0003 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

laravel-specialist

Build and configure Laravel 10+ applications, including creating Eloquent models and relationships, implementing Sanctum authentication, configuring Horizon queues, designing RESTful APIs with API resources, and building reactive interfaces with Livewire. Use when creating Laravel models, setting up queue workers…

Jeffallan/claude-skills · 86 tokens

laravel-security

Laravel security best practices for authn/authz, validation, CSRF, mass assignment, file uploads, secrets, rate limiting, and secure deployment.

hashgraph-online/awesome-codex-plugins · 34 tokens

integration-fixture

Create or validate a .test integration fixture under tests/php/Integration/Fixtures.

phel-lang/phel-lang · 16 tokens

create-module

Scaffold a new Marko module — a self-contained Composer package with composer.json, namespaced src/, and Pest tests. Use this skill whenever the user asks to create, add, or scaffold a new Marko module or package. Concrete triggers: 'create a module named payment', 'scaffold an acme/blog package', 'add a new module…

marko-php/marko · 120 tokens

llamaindex-development

Expert guidance for LlamaIndex development including RAG applications, vector stores, document processing, query engines, and building production AI applications.

Mindrally/skills · 32 tokens

Behat BDD Testing

PHP BDD testing with Behat framework using Gherkin feature files, Mink browser extension, context classes, and Symfony integration for behavior-driven acceptance testing.

PramodDutta/qaskills · 37 tokens