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.
curl -O https://raw.githubusercontent.com/autopkg/dataJAR-recipes/master/.github/skills/autopkg-recipes/SKILL.mdgit clone --depth 1 https://github.com/autopkg/dataJAR-recipesWrote 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.
[](https://agentmods.dev/skills/autopkg/datajar-recipes/autopkg-recipes)<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.
<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>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.
| Model | Per session | Once 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 |
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 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:
- Application name (as shown in Finder)
- Developer name
- Download method (Direct URL / Sparkle / GitHub Releases / Web Scraping)
- Download URL or source
- File format (.dmg / .pkg / .zip / .app)
- Architecture (Universal / Intel / Apple Silicon / Separate downloads)
- Recipe types needed (download / munki / pkg)
- Bundle ID (if known)
- Code signature info (if known)
- 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.dmg→TheUnarchiver) - 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.
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.
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.
- 3d ago Changed · +1 lines 0ce11b1d22e0
- 12d ago First seen · 476 lines · 101 tokens per session scan C 3d40f8765fe8
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…