dataJAR-recipes: Skill for Claude Code

.github/skills/autopkg-recipes/SKILL.md

autopkg-recipes is a skill for Claude Code, Codex from autopkg/dataJAR-recipes. It costs 101 tokens per session (6,560 once invoked), scanned C, original, Apache-2.0.

A guide and workflow for creating and checking AutoPkg recipes for macOS software. AutoPkg recipes describe how to download applications and prepare them for tools such as Munki, a Mac software-distribution system.

In plain words
What is it for?
Use it to create or repair download, Munki, and package recipes; support Intel or Apple Silicon downloads; scrape release URLs; and validate recipe structure.
Why use it?
It helps keep recipes consistent with the dataJAR repository’s naming, formatting, and validation rules. It also covers details such as CPU architecture, minimum macOS versions, and code-signature checks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is autopkg/dataJAR-recipes's own configuration. It tells Claude Code and Codex how to work on dataJAR-recipes 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 dataJAR-recipes configures →

Reuse

Borrowing it

Nothing to install: this file belongs to autopkg/dataJAR-recipes. 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/autopkg/dataJAR-recipes/master/.github/skills/autopkg-recipes/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/autopkg/dataJAR-recipes

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 autopkg-recipes

README.md
[![agentmods](https://agentmods.dev/badge/skills/autopkg/datajar-recipes/autopkg-recipes/github.svg)](https://agentmods.dev/skills/autopkg/datajar-recipes/autopkg-recipes)
Your own site
<a href="https://agentmods.dev/skills/autopkg/datajar-recipes/autopkg-recipes"><img src="https://agentmods.dev/badge/skills/autopkg/datajar-recipes/autopkg-recipes/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 autopkg-recipes

Your own site · 80×15
<a href="https://agentmods.dev/skills/autopkg/datajar-recipes/autopkg-recipes"><img src="https://agentmods.dev/badge/skills/autopkg/datajar-recipes/autopkg-recipes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,560 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00101 $0.06560
Opus 5 $0.00051 $0.03280
Sonnet 5 $0.00020 $0.01312
Haiku 4.5 $0.00010 $0.00656

Measured 3d ago against content hash 0ce11b1d22e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

autopkg-recipes scanned grade C with 2 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 3d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s "https://api.github.com/repos/OWNER/REPO/releases" | python3 -c "import sys,json; [print(f'{r[\"tag_name\"]}: prerelease={r[\"prerelease\"]}') for r in json.load(sys.stdin)]"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://raw.githubusercontent.com/autopkg/index/main/v1/index.json" -o /tmp/autopkg-index.json
.github/skills/autopkg-recipes/SKILL.md · 477 lines

How it starts

The opening of the file, as written. The whole thing — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AutoPkg Recipe Creation

Create, review, and fix AutoPkg recipes following dataJAR-recipes conventions.

When to Use

  • Creating new AutoPkg download, munki, or pkg recipes
  • Reviewing existing recipes for standards compliance
  • Fixing formatting, naming, or structural issues in recipes
  • Adding architecture support to existing recipes
  • Adding minimum OS version detection to munki recipes

Information Gathering

Before creating recipes, collect these details from the user:

  1. Application name (as shown in Finder)
  2. Developer name
  3. Download method (Direct URL / Sparkle / GitHub Releases / Web Scraping)
  4. Download URL or source
  5. File format (.dmg / .pkg / .zip / .app)
  6. Architecture (Universal / Intel / Apple Silicon / Separate downloads)
  7. Recipe types needed (download / munki / pkg)
  8. Bundle ID (if known)
  9. Code signature info (if known)
  10. Special requirements (dependencies, scripts, etc.)

Procedure

Step 1: Derive App Name from URL

Before searching for existing recipes, derive the actual app name from the download URL and any available metadata. This mirrors Recipe Robot's flow — it downloads and inspects the app to get CFBundleName before searching.

URL Analysis:

  • Parse the filename from the URL (e.g., TheUnarchiver.dmgTheUnarchiver)
  • Look for bundle ID patterns in URL path segments (e.g., com.macpaw.site.theunarchiver)
  • If the URL points to a Sparkle appcast, fetch it to extract the app name and download URL
  • If the user provided an app name, use it — but also check variations (with/without spaces, articles like "The")

Normalise the app name for searching by stripping spaces, dots, commas, and hyphens, then lowercasing. For example:

  • "The Unarchiver" → theunarchiver
  • "Visual Studio Code" → visualstudiocode
  • "BBEdit" → bbedit

Step 2: Check for Existing Recipes

Search for existing AutoPkg recipes using the app name derived in Step 1. Recipes may already exist in community repositories that can be used as-is, overridden, or used as parent recipes.

Read the full file on GitHub · 477 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago Changed · +1 lines 0ce11b1d22e0
  2. 12d ago First seen · 476 lines · 101 tokens per session scan C 3d40f8765fe8

Subscribe to this mod's changes

autopkg-recipes is a skill published in the GitHub repository autopkg/dataJAR-recipes (130 stars, last pushed 2d ago), licensed Apache-2.0. It adds 101 tokens to every session and 6,560 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens