laravel-auditor: Skill for Claude Code

.agents/skills/package-testing/SKILL.md

package-testing is a skill for Claude Code, Codex from MrPunyapal/laravel-auditor. It costs 61 tokens per session (439 once invoked), scanned A, a copy of package-testing, MIT.

A testing guide for Laravel packages using Pest and Orchestra Testbench. TDD means writing a failing test first, then adding the code that makes it pass.

In plain words
What is it for?
Use it to write or review tests for package commands, routes, configuration, migrations, published files, and other integration behavior.
Why use it?
It gives package changes a repeatable way to prove they work, including normal use, errors, edge cases, and type-related problems.

Skill for Claude CodeCodex

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

This is MrPunyapal/laravel-auditor's own configuration. It tells Claude Code and Codex how to work on laravel-auditor 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 laravel-auditor configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MrPunyapal/laravel-auditor. 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/MrPunyapal/laravel-auditor/main/.agents/skills/package-testing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/MrPunyapal/laravel-auditor

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-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/mrpunyapal/laravel-auditor/package-testing/github.svg)](https://agentmods.dev/skills/mrpunyapal/laravel-auditor/package-testing)
Your own site
<a href="https://agentmods.dev/skills/mrpunyapal/laravel-auditor/package-testing"><img src="https://agentmods.dev/badge/skills/mrpunyapal/laravel-auditor/package-testing/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 package-testing

Your own site · 80×15
<a href="https://agentmods.dev/skills/mrpunyapal/laravel-auditor/package-testing"><img src="https://agentmods.dev/badge/skills/mrpunyapal/laravel-auditor/package-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 439 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 100% copy Near-identical to another mod 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 $0.00061 $0.00439
Opus 5 $0.00030 $0.00219
Sonnet 5 $0.00012 $0.00088
Haiku 4.5 $0.00006 $0.00044

Measured 11d ago against content hash 971f3581ae43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

package-testing 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 11d 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

This is a copy

100% identical to package-testing — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/package-testing/SKILL.md · 44 lines

What it actually says

Package Testing

Primary Goal

Prove package behavior with Pest 4/5, Orchestra Testbench, and the local tests/TestCase.php setup before or alongside implementation.

Workflow

  1. Start with TDD: write the smallest failing package test for the requested behavior, then implement the smallest change that makes it pass.
  2. Cover happy-path, unhappy-path, and edge-case behavior when the feature has meaningful failure modes.
  3. Prefer focused feature tests for package integration behavior and arch tests for broad constraints.
  4. Use composer test:unit -- --filter ... while iterating, composer test:types when type-sensitive tests or code changed, and composer test before finishing.
  5. Keep real package tests in the suite and remove only throwaway tests that were explicitly created for local scaffolding experiments.

References

  • tests/TestCase.php
  • tests/Pest.php
  • tests/Feature/
  • tests/Unit/
  • tests/ArchTest.php
  • composer.json scripts

Examples

  • Test config merge and config override by asserting default package config, then overriding the host config value in the Testbench app.
  • Test publishable assets, migrations, views, lang files, or config by invoking vendor publish behavior and asserting the target path exists.
  • Test routes with Testbench HTTP requests, commands with Artisan assertions, migrations with a SQLite test database, and workbench behavior after composer build when needed.

Anti-Patterns

  • Deleting real package tests because they are inconvenient.
  • Relying only on smoke tests when behavior needs assertions.
  • Testing implementation details when observable package behavior is available.
  • Keeping throwaway scaffolding experiment tests in the package test suite.
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. 11d ago First seen · 44 lines · 61 tokens per session scan A 971f3581ae43

Subscribe to this mod's changes

package-testing is a skill published in the GitHub repository MrPunyapal/laravel-auditor (46 stars, last pushed 4d ago), licensed MIT. It adds 61 tokens to every session and 439 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to package-testing, differing in 0 lines, and is treated as a copy.