homebrew-multi-formula

homebrew-multi-formula is a skill for Claude Code, Codex from Data-Wise/craft. It costs 51 tokens per session (2,522 once invoked), scanned A, original, MIT.

A release coordinator for multiple Homebrew formulas. Homebrew is a package manager commonly used to install developer tools on macOS and Linux.

In plain words
What is it for?
Use it for batch updates, monorepo releases, and related packages that need dependency-aware release ordering. A monorepo is one repository containing multiple packages.
Why use it?
It helps prevent packages from being released in the wrong order when one formula depends on another.

Skill for Claude CodeCodex

Part of the craft plugin — 31 skills, 22 commands, 2 agents, 1 MCP server 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 skills/data-wise/craft/homebrew-multi-formula
Any agent
npx skills add Data-Wise/craft --skill homebrew-multi-formula
Clone the repo
git clone --depth 1 https://github.com/Data-Wise/craft

Made for: Claude Code, Codex.

Or install craft, the plugin that ships this one along with the rest of its 31 skills, 22 commands, 2 agents, 1 MCP server.

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 homebrew-multi-formula

README.md
[![agentmods](https://agentmods.dev/badge/skills/data-wise/craft/homebrew-multi-formula.svg)](https://agentmods.dev/skills/data-wise/craft/homebrew-multi-formula)
Your own site
<a href="https://agentmods.dev/skills/data-wise/craft/homebrew-multi-formula"><img src="https://agentmods.dev/badge/skills/data-wise/craft/homebrew-multi-formula.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,522 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 $0.00051 $0.02522
Opus 5 $0.00026 $0.01261
Sonnet 5 $0.00010 $0.00504
Haiku 4.5 $0.00005 $0.00252

Measured 3d ago against content hash b647bc04b2d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

homebrew-multi-formula 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 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.

Makes network callslowCapability

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

CORE_SHA=$(curl -sL "https://github.com/.../v${{ inputs.core_version }}.tar.gz" | shasum -a 256 | cut -d' ' -f1)
skills/distribution/homebrew-multi-formula/SKILL.md · 356 lines

How it starts

The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Formula Coordinator

Coordinate releases across multiple Homebrew formulas, respecting dependency order and handling batch updates.

Surface scope: Homebrew installs plugins to the Claude Code CLI surface (~/.claude/). Claude Desktop (DXT/MCPB extensions — a different, MCP-server format) and Cowork are separate surfaces; see dist-extras and commands/dist/surfaces.md for the full model.

Use Cases

  1. Monorepo Releases - Multiple packages from one repository
  2. Ecosystem Releases - Related packages with dependencies (e.g., rforge ecosystem)
  3. Batch Updates - Update multiple formulas in one PR
  4. Dependency Chains - Release in correct order when packages depend on each other

Dependency Detection

Formula Dependencies

# In myapp-cli.rb
depends_on "myapp-core"  # Runtime dependency

# In myapp-plugin.rb
depends_on "myapp-cli"   # Also depends on cli

Build Order

myapp-core    →  myapp-cli    →  myapp-plugin
    ↓              ↓
    └──────────────┴──────→ (can release in parallel after core)

Workflow: Batch Release

Input Manifest

Create .homebrew-batch.yml:

# Batch release configuration
tap: data-wise/tap
auto_merge: true

formulas:
  - name: myapp-core
    version: "2.0.0"
    source: github

  - name: myapp-cli
    version: "2.0.0"
    source: github
    depends_on:
      - myapp-core

  - name: myapp-plugin
    version: "1.5.0"
    source: pypi
    depends_on:
      - myapp-cli

Execution Order

Step 1: Build dependency graph
────────────────────────────────
  myapp-core (no deps) → Level 0
  myapp-cli (deps: core) → Level 1
  myapp-plugin (deps: cli) → Level 2

Step 2: Release in waves
────────────────────────────────
  Wave 0: myapp-core
    ✓ Updated formula
    ✓ PR created: #42
    ✓ Auto-merged

  Wave 1: myapp-cli
    ⏳ Waiting for Wave 0...
    ✓ Updated formula
    ✓ PR created: #43
    ✓ Auto-merged

  Wave 2: myapp-plugin
    ⏳ Waiting for Wave 1...
    ✓ Updated formula
    ✓ PR created: #44
    ✓ Auto-merged

Step 3: Summary
────────────────────────────────
  ✓ 3 formulas updated
  ✓ 3 PRs merged
  ⏱ Total time: 4m 23s

Read the full file on GitHub · 356 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. 3d ago First seen · 356 lines · 51 tokens per session scan A b647bc04b2d4

Subscribe to this mod's changes

homebrew-multi-formula is a skill published in the GitHub repository Data-Wise/craft (4 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 2,522 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

platform-operations

Unified platform operations guidance for CI/CD pipeline design, deployment strategies, observability, SLI/SLOs, and incident-ready rollouts. Use when building release workflows, production monitoring, or reliability controls.

rsmdt/the-startup · 45 tokens

mandu-mcp-deploy

빌드/배포 파이프라인 워크플로우. "배포", "deploy", release 전 자동 호출. deploy.check 는 fail-fast 게이트. deploy.preview 로 프로덕션 리허설. manual build + guard + seo 나열 대신 aggregate 도구 사용.

konamgil/mandu · 65 tokens

mandu-deploy

프로덕션 배포 파이프라인. Docker/CI-CD/nginx.

konamgil/mandu · 20 tokens

github-actions-workflow

Scaffolds or audits a GitHub Actions CI/CD workflow for a project. Covers job structure, caching, secrets handling, concurrency groups, environment gates, and reusable workflows via workflowcall. Invoked when the user asks to set up CI, add a GitHub Actions workflow, improve pipeline performance, or share workflow…

soulcodex/agentic · 72 tokens

watch-patterns

Correct construction of watchers for long-running operations. TRIGGER when: arming observation of a long-running operation (CI run, deploy, transfer, GC/prune, log stream), writing poll/until loops, or using the Monitor tool. SKIP: defining production alerts/metrics (use monitoring-observability); log formatting (use…

komluk/scaffolding · 76 tokens

loop-on-ci

Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.

Kripu77/software-factory · 28 tokens