package-release

package-release is a skill for Claude Code, Codex from laravel/package-skeleton. It costs 44 tokens per session (357 once invoked), scanned A, original, MIT.

A release-preparation guide for Laravel packages, which are reusable PHP components for the Laravel web framework. It checks release files and drafts the steps without publishing the release.

In plain words
What is it for?
Use it to review package changes, update or check release notes, run Composer tests, inspect GitHub release workflows, and prepare a release command.
Why use it?
It reduces the risk of missing changelog entries, using the wrong version or tag, or releasing untested changes. Publishing still requires the user's approval.

Skill for Claude CodeCodex

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

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/package-skeleton/package-release
Any agent
npx skills add laravel/package-skeleton --skill package-release
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-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/laravel/package-skeleton/package-release.svg)](https://agentmods.dev/skills/laravel/package-skeleton/package-release)
Your own site
<a href="https://agentmods.dev/skills/laravel/package-skeleton/package-release"><img src="https://agentmods.dev/badge/skills/laravel/package-skeleton/package-release.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 357 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 5.1 $0.00044 $0.00357
Opus 5 $0.00022 $0.00179
Sonnet 5 $0.00009 $0.00071
Haiku 4.5 $0.00004 $0.00036

Measured 5d ago against content hash 60f93c34f96f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

package-release 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/package-release/SKILL.md · 42 lines

What it actually says

Package Release

Primary Goal

Prepare a safe package release checklist and implementation without tagging, pushing, or publishing unless the user explicitly approves that action.

Workflow

  1. Review CHANGELOG.md, generated release notes config, GitHub release workflows, open diff, and pending package changes.
  2. Validate the release state with composer test before recommending a release.
  3. Confirm whether version metadata needs to change; many Laravel packages rely on Git tags rather than a hardcoded package version.
  4. Review tag naming, release branch, and GitHub release workflow behavior before any release command.
  5. Do not tag, push, or publish without explicit user approval.

References

  • CHANGELOG.md
  • .github/release.yml
  • .github/workflows/update-changelog.yml
  • .github/workflows/tests.yml
  • composer.json

Examples

  • Prepare a release by checking changelog coverage, confirming generated release notes categories, running composer test, and drafting the tag command for user approval.
  • Update release notes grouping in .github/release.yml when a new label convention is added.

Anti-Patterns

  • Creating tags, pushing branches, or publishing releases without explicit approval.
  • Skipping composer test before a release recommendation.
  • Treating generated release notes as a replacement for meaningful CHANGELOG.md entries.
  • Changing release workflows without checking the supported matrix in .github/workflows/tests.yml.
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 · 42 lines · 44 tokens per session scan A 60f93c34f96f

Subscribe to this mod's changes

package-release is a skill published in the GitHub repository laravel/package-skeleton (60 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 357 once invoked, about $0.0002 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.