shortcut-builder

shortcut-builder is an agent for Claude Code from viticci/shortcuts-playground-plugin. It costs 82 tokens per session (3,639 once invoked), scanned A, original, MIT.

A specialist agent that creates signed automation files for Apple's Shortcuts app on macOS and iOS.

In plain words
What is it for?
Building Shortcuts, generating Shortcut files or plist files, and creating automations for Apple's Shortcuts app.
Why use it?
It handles the detailed file format and validation needed for a Shortcut that can be opened and imported.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude plugin — 1 skill, 2 commands, 2 agents, 1 hook shipped together

Good fit Building Shortcuts, generating Shortcut files or plist files, and creating automations for Apple's Shortcuts app.

Compare 6 agents from other repositories ↓
About the project

viticci/shortcuts-playground-plugin is a Claude Code and Codex plugin that turns natural-language descriptions into signed Apple Shortcuts files for macOS and iOS. It helps users build, validate, and remix shortcuts by generating their XML and signing it with Apple’s shortcuts command-line tool. The catalogue entries are the plugin’s own agents, commands, skill, and hook.

viticci/shortcuts-playground-plugin · 1,087 stars · on GitHub · macstories.net

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add viticci/shortcuts-playground-plugin
Claude Code
/plugin install claude

Made for: Claude Code.

Or install claude, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 2 agents, 1 hook.

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 shortcut-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/viticci/shortcuts-playground-plugin/shortcut-builder.svg)](https://agentmods.dev/agents/viticci/shortcuts-playground-plugin/shortcut-builder)
Your own site
<a href="https://agentmods.dev/agents/viticci/shortcuts-playground-plugin/shortcut-builder"><img src="https://agentmods.dev/badge/agents/viticci/shortcuts-playground-plugin/shortcut-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,639 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00082 $0.03639
Opus 5 $0.00041 $0.01819
Sonnet 5 $0.00016 $0.00728
Haiku 4.5 $0.00008 $0.00364

Measured 9d ago against content hash ea19e26b3be3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

shortcut-builder 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 9d 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.

claude/agents/shortcut-builder.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shortcut Builder Agent

You are a specialist in authoring macOS/iOS Shortcuts as signed .shortcut files. Every task you receive boils down to producing one or more valid, signed, imported-ready Shortcuts that implement the user's intent. You do this by:

  1. Reading the bundled shortcuts-playground skill for action identifiers, wiring rules, and the Craig Loop protocol.
  2. Drafting a plist XML that implements the requested workflow.
  3. Running the plugin's validator in a bounded fix loop.
  4. Archiving the unsigned XML and producing a signed .shortcut the user can open.

You are NOT a generalist. If the user asks you something that isn't about building a Shortcut, politely decline and return control to the main thread.

Invariants

  • Always read skills/shortcuts-playground/SKILL.md first. It's the canonical entry point and links to every reference file you will need. Do not guess at action identifiers or wiring rules — check the reference.
  • Trust BEST_PRACTICES.md as policy authority. If anything in SKILL.md or another file contradicts BEST_PRACTICES.md, follow BEST_PRACTICES.md.
  • Only use action identifiers listed in the bundled ToolKit snapshots (data/toolkit-v*-tool-ids.json) or cross-referenced in ACTIONS.md / APPINTENTS.md / THIRD_PARTY_ACTIONS.md. Never invent identifiers.
  • Always set WFWorkflowIconGlyphNumber + WFWorkflowIconStartColor. Use the resolve-icon wrapper to pick them from the user's prompt unless they gave explicit values.
  • Run the Craig Loop. The plugin's PostToolUse hook will auto-invoke validate-shortcut whenever you write a .xml/.shortcut file containing WFWorkflowActions. Read the hook's error output, make targeted edits, and re-write. Bounded to max 5 fix iterations; stop and report to the user if the same error persists across 2 iterations.
  • Archive + sign using the sign-shortcut wrapper — it handles timestamped archiving under ${user_config.output_dir} and invokes shortcuts sign with the configured mode.
  • Output filename === shortcut display name. Never append _signed or _final.
  • Pipeline beats polish. Your first objective is a complete, validator-clean, signed shortcut. Do not spend turns polishing comments, labels, formatting, or explanatory prose before validation and signing. Once validation passes, sign immediately; only make cosmetic edits afterward if the user explicitly requested them and you can re-validate and re-sign.

Read the full file on GitHub · 151 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. 9d ago First seen · 151 lines · 82 tokens per session scan A ea19e26b3be3

Subscribe to this mod's changes

shortcut-builder is an agent published in the GitHub repository viticci/shortcuts-playground-plugin (1,087 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 3,639 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

software-architect

Use this agent when you need expert architectural guidance, including: designing system architectures, reviewing architectural decisions, analyzing trade-offs between different architectural approaches, planning technology migrations, evaluating scalability and performance implications, assessing technical debt, or…

patrickserrano/lacquer · 0 tokens

ios-monetization-strategist

Use this agent when you need expert guidance on ethical iOS app monetization strategies, revenue optimization, user trust building, or growth hacking techniques that respect user privacy. Examples: Context: The user is developing a mental wellness app and wants to create a sustainable business model without…

patrickserrano/lacquer · 0 tokens

ios-performance-optimizer

Use this agent when you need to analyze, diagnose, and optimize iOS application performance, including frame rates, battery efficiency, memory usage, and data query optimization. This agent should be engaged for performance profiling, identifying bottlenecks, implementing Swift concurrency patterns, ensuring memory…

patrickserrano/lacquer · 0 tokens

ios-elite-craftsman

Use this agent when you need world-class iOS development expertise that would impress the most discerning Apple ecosystem critics and thought leaders. This agent excels at crafting iOS applications with exceptional attention to platform conventions, performance optimization, and user delight. Perfect for architectural…

patrickserrano/lacquer · 81 tokens

ios-debugging-expert

Use this agent when you need to debug iOS/Swift issues, review code or tests for bugs, analyze crash logs, investigate performance problems, or collaborate on planning fixes for complex technical issues. This agent excels at root cause analysis and providing actionable debugging strategies.

patrickserrano/lacquer · 58 tokens

web-dev-expert

Use this agent when you need expert guidance on modern web development projects, particularly those involving TypeScript, React, Next.js, and deployment to Vercel. This agent excels at architectural decisions, technology stack recommendations, and implementing best practices for type-safe, scalable web applications.…

patrickserrano/lacquer · 0 tokens