mcp-server-ios-shortcuts: Instructions file for Codex

AGENTS.md

mcp-server-ios-shortcuts AGENTS.md is an instructions file for Codex, OpenCode from truth0530/mcp-server-ios-shortcuts. It costs 1,395 tokens per session, scanned B, original, MIT.

Repository instructions for an MCP server that builds, signs, imports, runs, and inspects macOS and iOS Shortcuts, which are Apple’s visual automation files.

In plain words
What is it for?
Use them when creating, decompiling, modifying, validating, signing, importing, running, or learning from .shortcut files on macOS or iOS.
Why use it?
They define the safe workflow for editing real Shortcut files, including validation, platform targeting, signing, and checks for system access. They also warn about requirements such as Full Disk Access on macOS.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads ~/.codex paths; mentions Codex.

This is truth0530/mcp-server-ios-shortcuts's own configuration. It tells Codex and OpenCode how to work on mcp-server-ios-shortcuts itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-server-ios-shortcuts configures →

Reuse

Borrowing it

Nothing to install: this file belongs to truth0530/mcp-server-ios-shortcuts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/truth0530/mcp-server-ios-shortcuts/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/truth0530/mcp-server-ios-shortcuts

Made for: Codex, OpenCode.

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 mcp-server-ios-shortcuts AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/truth0530/mcp-server-ios-shortcuts/agents-md/github.svg)](https://agentmods.dev/instructions/truth0530/mcp-server-ios-shortcuts/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/truth0530/mcp-server-ios-shortcuts/agents-md"><img src="https://agentmods.dev/badge/instructions/truth0530/mcp-server-ios-shortcuts/agents-md/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 mcp-server-ios-shortcuts AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/truth0530/mcp-server-ios-shortcuts/agents-md"><img src="https://agentmods.dev/badge/instructions/truth0530/mcp-server-ios-shortcuts/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,395 This file is loaded in full into every session.
When invoked 1,395 The same file — it is already loaded in full.
Security scan B 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 $0.01395 $0.01395
Opus 5.5 $0.00558 $0.00558
Sonnet 5.5 $0.00279 $0.00279
Haiku 4.5 $0.00139 $0.00139

Measured 2mo ago against content hash b1ef744ec6ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

mcp-server-ios-shortcuts AGENTS.md scanned grade B 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 2mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| Codex CLI | `~/.codex/config.toml` → `[mcp_servers.ios-shortcuts]` |
AGENTS.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent notes — ios-shortcuts MCP (v2.9.2)

Purpose

Build, sign, import, list, run, and inspect macOS/iOS Shortcuts (.shortcut) via MCP tools. Zero pip deps. macOS only.

Preferred workflow

  1. doctor — confirm CLI + sign probe + allow roots
  2. Prefer curated short names for production quality
  3. Existing library shortcut (critical):
    • export_library_shortcut or user export to disk
    • extract_signed_shortcut / decompile_shortcut (AEA1 decrypt)
    • clone_shortcut to fork under a new name
    • Diff real identifiers before inventing a “fix”
  4. For files you already have: decompile_shortcut → edit → validate_recipe → rebuild
  5. After library changes: learn_from_corpus / extract_system_library
    • Needs Full Disk Access for Shortcuts.sqlite
    • Never trust self-bootstrap unless debugging
  6. Generic short keys only if accepted map exists (get_learned_params)
  7. Remap → schema-aware coercion (enums plain; text may token-wrap)
  8. App Intents: type: app_intent with reverse-DNS identifier
  9. validate_recipe with target_platform (ios/macos)
  10. build_shortcut — keep raw_path for inspect/decompile/learn
  11. run_shortcut when installed (safe_mode blocks)

Never improve a real user shortcut by guessing IDs without extract.
Docs: docs/CLONE_AND_EXTRACT.md

Sign before shipping to the user

shortcuts sign -m anyone -i Name_raw.shortcut -o Name.shortcut

Do not use --mode / --input / --output (agents have failed with “incorrect format”).
Do not claim “개선 완료” with only *_raw.shortcut — iPhone needs the signed file.

Build result shape

{
  "ok": true,
  "path": "/…/Name.shortcut",
  "raw_path": "/…/Name_raw.shortcut",
  "signed_path": "/…/Name.shortcut",
  "signed": true,
  "actions_summary": [{ "index": 0, "type": "delay", "…": "…" }],
  "warnings": [],
  "risks": []
}

Import tools report import_status: "import_prompted" — GUI confirm may still be required.

Read the full file on GitHub · 106 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. 2mo ago First seen · 106 lines · 1,395 tokens per session scan B b1ef744ec6ba

Subscribe to this mod's changes

mcp-server-ios-shortcuts AGENTS.md is an instructions file published in the GitHub repository truth0530/mcp-server-ios-shortcuts (12 stars, last pushed 2mo ago), licensed MIT. It adds 1,395 tokens to every session, about $0.0056 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

mcp-server-ios-shortcuts AGENTS.md compared with instructions from other repositories

mcp-server-ios-shortcuts AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-server-ios-shortcuts AGENTS.mdtruth0530/mcp-server-ios-shortcutsInstructions file122mo agoMITB1,395Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode