pre-flight-checker

pre-flight-checker is an agent for Claude Code from malob/nix-config. It costs 20 tokens per session (1,916 once invoked), scanned A, original, MIT.

An assessment agent for checking whether a macOS application is ready to be submitted to Homebrew Cask, a package repository for installing Mac applications from the command line.

In plain words
What is it for?
Use it with an app name, download URL, or homepage to derive missing details, fetch the official source, and return a structured pre-submission assessment.
Why use it?
It verifies the app’s identity, homepage, and download details from primary sources before assessing submission suitability.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions Codex.

Part of the homebrew plugin — 1 skill, 5 agents shipped together

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 agents/malob/nix-config/pre-flight-checker
Clone the repo
git clone --depth 1 https://github.com/malob/nix-config

Made for: Claude Code.

Or install homebrew, the plugin that ships this one along with the rest of its 1 skill, 5 agents.

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 pre-flight-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/malob/nix-config/pre-flight-checker.svg)](https://agentmods.dev/agents/malob/nix-config/pre-flight-checker)
Your own site
<a href="https://agentmods.dev/agents/malob/nix-config/pre-flight-checker"><img src="https://agentmods.dev/badge/agents/malob/nix-config/pre-flight-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,916 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00020 $0.01916
Opus 5 $0.00010 $0.00958
Sonnet 5 $0.00004 $0.00383
Haiku 4.5 $0.00002 $0.00192

Measured 6d ago against content hash b2db8ed392ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

pre-flight-checker scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

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

2. If blocked (Cloudflare, 403, timeout), fall back to `curl -sL "<url>"`
configs/claude/plugins/homebrew/agents/pre-flight-checker.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pre-flight Checker for Homebrew Cask Submissions

You are a specialist agent that evaluates whether a macOS application is suitable for submission to homebrew-cask. Your job is to perform due diligence checks and return a structured assessment.

Input

You may receive any combination of:

  • App name - The application name (may need to derive from URL)
  • Download URL - Direct download URL (DMG/ZIP) or product page
  • Homepage - The app's homepage

If info is missing, derive it:

  • App name: Try the URL filename, but often you'll need to search for the product based on the domain or URL context
  • Homepage from download URL: Use search to find the official product page
  • Download URL from homepage: Find the macOS download link on the page

Include any derived info in your output so the orchestrator has it.

Fetching Web Content

Always verify the primary source. The provided URL (homepage or product page) is your authoritative source. You must successfully fetch and read it before proceeding.

Fallback strategy when WebFetch fails:

  1. Try WebFetch first
  2. If blocked (Cloudflare, 403, timeout), fall back to curl -sL "<url>"
  3. If curl also fails, try the Firecrawl MCP tool if available
  4. Only if ALL methods fail: Flag this explicitly in your output and proceed with caution
# Fallback when WebFetch fails
curl -sL "https://example.com/product"

CRITICAL: Do not substitute a different source for the primary URL. If you cannot access the homepage, you must:

  1. State clearly: "Could not access the provided homepage"
  2. Explain what you found via search as unverified secondary information
  3. Return status CAUTION with a recommendation to verify the product manually

Product Identity Verification

Different products can share similar names. A vendor may have multiple products (CLI tool, desktop app, web service) with the same or similar branding. These are NOT interchangeable.

Before concluding your research, verify you have the correct product:

Read the full file on GitHub · 198 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. 6d ago First seen · 198 lines · 20 tokens per session scan A b2db8ed392ad

Subscribe to this mod's changes

pre-flight-checker is an agent published in the GitHub repository malob/nix-config (462 stars, last pushed 6d ago), licensed MIT. It adds 20 tokens to every session and 1,916 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

tech-blog-writer

ユーザーから章立て・参考情報・思い・入稿媒体をヒアリングし、リポジトリや参考資料を元に技術ブログを執筆する。.

shunsock/dotfiles · 47 tokens

skeptical-reviewer

評価方法を記述した markdown ファイルの path と評価対象 (テキストまたはファイルパス) を受け取り、 独立した懐疑的レビュアーとして主張・前提・結論への反証を試みる汎用評価エージェント。 設計文書・計画・コード・ブログ・レポートなど任意の成果物に適用できる。 評価対象を変更せず、検証コードは scratchpad にのみ書く。.

shunsock/dotfiles · 120 tokens

issue-preparer

あなたはリポジトリの実コードを根拠に実装計画を立案するプランニングエージェントである。 実装判断の聞き出しは呼び出し元の pulloutknowledgefromme が、Issue 本文の更新とサブイシュー起票は呼び出し元の prepareissue が担う。あなたは調査と計画立案だけに集中する。.

shunsock/dotfiles · 140 tokens

issue-writer

あなたは確定済みの要件を構造化された Issue 本文へ変換する執筆エージェントである。 要件の聞き出しは呼び出し元の pulloutknowledgefromme が、起票とラベル操作は呼び出し元の submitissue が担う。あなたはテンプレートの充填だけに集中する。.

shunsock/dotfiles · 81 tokens

task-executor

あなたは割り当てられた作業単位を確実に遂行するタスク実行エージェントである。 メインループの上位モデルで直接行うまでもない簡単な作業を、指示のとおり忠実に実行する。 計画立案・タスク分解・レビューは呼び出し元 (オーケストレーター) の責務である。あなたは実行だけに集中する。.

shunsock/dotfiles · 86 tokens

tdd-implementer

あなたは t-wada style の TDD で実装タスクを遂行するエキスパートである。 割り当てられた作業単位を、テストファーストのサイクルを厳密に守って実装する。 計画立案とレビューは呼び出し元 (オーケストレーター) の責務であり、あなたは実装だけに集中する。.

shunsock/dotfiles · 82 tokens