agentmods.dev

shortcuts-builder

shortcuts-builder is a skill for Claude Code, Codex from OpenMinis/MinisSkills. It costs 62 tokens per session (4,762 once invoked), scanned C, original, MIT.

A skill for turning a plain-language automation request into an Apple Shortcut, Apple's visual automation format. It can plan the action sequence, create shortcut XML, validate it locally, and route work between pure Shortcut and hybrid approaches.

In plain words
What is it for?
Use it for automations involving notes, reminders, weather, sharing, URLs, files, and related iPhone or iPad tasks.
Why use it?
It helps translate an informal request into the structured actions and file format that Shortcuts needs.

Skill for Claude CodeCodex

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

not rated 502repo +45 2d ago C scan 62 tokens original MIT

Good fit Use it for automations involving notes, reminders, weather, sharing, URLs, files, and related iPhone or iPad tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openminis/minisskills/shortcuts-builder
View source ↗ OpenMinis/MinisSkills
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.

Any agent
npx skills add OpenMinis/MinisSkills --skill shortcuts-builder
Clone the repo
git clone --depth 1 https://github.com/OpenMinis/MinisSkills

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 shortcuts-builder

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/openminis/minisskills/shortcuts-builder"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/shortcuts-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,762 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00062 $0.04762
Opus 5.5 $0.00025 $0.01905
Sonnet 5.5 $0.00012 $0.00952
Haiku 4.5 $0.00006 $0.00476

Measured 12d ago against content hash f259deac8a49, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

shortcuts-builder scanned grade C 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 12d 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

scripts/sign-shortcut --setup-mac user@host --key ~/.ssh/id_ed25519
shortcuts-builder/SKILL.md · 452 lines

How it starts

The opening of the file, as written. The whole thing — 452 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shortcuts Builder

Language

Reply to the user in the user's language (e.g. Chinese question -> Chinese answer). The skill files themselves are English.

Goal

Reliably turn natural-language automation requests into one or more of the following results:

  • A judgment on whether the task should be built as a shortcut first
  • A route choice: pure Shortcuts / Hybrid / not-shortcut-first
  • Action-chain planning
  • An unsigned XML draft
  • Locally validated XML
  • A signed .shortcut product

This skill is an adaptation of the upstream viticci/shortcuts-playground-plugin (MIT) for Minis on iPhone/iPad. It keeps the upstream knowledge base and methods, and adds Minis-oriented routing, clarification, an environment profile, build checks, and delivery logic. See UPSTREAM_ATTRIBUTION.md.

Quick Path (read this first)

For a typical request, do these in order. Every item is detailed later; this is the map.

  1. Decide the route (BUILD_CHECKLIST.md, CAPABILITY_DECISION.md). If the request is not shortcut-first, stop.
  2. Ask what is missing with user_ask (section 4). Use the recommended default on timeout, except for signing and uploads.
  3. Pick each action from the right source. Look at the identifier prefix:
    • is.workflow.actions.* -> first-party classic action -> ACTION_PARAM_INDEX.md
    • com.apple.* -> first-party App Intent -> APPINTENTS.md
    • anything else (<bundle id>.<Intent>) -> third-party App Intent -> THIRD_PARTY_INTENTS.md and scripts/appintent_catalog.py
  4. Draft unsigned XML in /var/minis/attachments/shortcut/drafts/, then validate (scripts/validate-shortcut) until it passes.
  5. Sign only if the user wants a finished file, after they have chosen a backend. Then verify the file header is AEA1.
  6. Report the route, the action chain, the paths, and anything left for the user (apps to install, parameters to pick in the editor).

Hard Constraints

Read the full file on GitHub · 452 lines

Files

What ships with it

60 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. 12d ago First seen · 452 lines · 62 tokens per session scan C f259deac8a49

Subscribe to this mod's changes

shortcuts-builder is a skill published in the GitHub repository OpenMinis/MinisSkills (502 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 4,762 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-08.

Productivity
Related

Other skills, from other repositories

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.

paperclipai/paperclip · 30 tokens

rowboat-spaces

How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.

rowboatlabs/rowboat · 60 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens