seiro-mcp-visionos-build-operator

seiro-mcp-visionos-build-operator is a skill for Codex from karad/seiro-mcp. It costs 86 tokens per session (1,408 once invoked), scanned B, original, MIT.

A guided workflow for building and diagnosing visionOS projects, Apple's software for spatial-computing devices, through Seiro MCP. It covers scheme inspection, sandbox-policy checks, builds, diagnostics, and build-output retrieval.

In plain words
What is it for?
Use it to discover Xcode schemes, validate sandbox settings, build a visionOS app, inspect failures, and retrieve output after a successful build.
Why use it?
It gives build failures a defined diagnostic path and keeps build operations in the available MCP workflow.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to discover Xcode schemes, validate sandbox settings, build a visionOS app, inspect failures, and retrieve output after a successful build.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/karad/seiro-mcp/seiro-mcp-visionos-build-operator
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 karad/seiro-mcp --skill seiro-mcp-visionos-build-operator
Clone the repo
git clone --depth 1 https://github.com/karad/seiro-mcp

Made for: 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 seiro-mcp-visionos-build-operator

README.md
[![agentmods](https://agentmods.dev/badge/skills/karad/seiro-mcp/seiro-mcp-visionos-build-operator/github.svg)](https://agentmods.dev/skills/karad/seiro-mcp/seiro-mcp-visionos-build-operator)
Your own site
<a href="https://agentmods.dev/skills/karad/seiro-mcp/seiro-mcp-visionos-build-operator"><img src="https://agentmods.dev/badge/skills/karad/seiro-mcp/seiro-mcp-visionos-build-operator/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 seiro-mcp-visionos-build-operator

Your own site · 80×15
<a href="https://agentmods.dev/skills/karad/seiro-mcp/seiro-mcp-visionos-build-operator"><img src="https://agentmods.dev/badge/skills/karad/seiro-mcp/seiro-mcp-visionos-build-operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,408 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00086 $0.01408
Opus 5 $0.00043 $0.00704
Sonnet 5 $0.00017 $0.00282
Haiku 4.5 $0.00009 $0.00141

Measured 12d ago against content hash 38a40f2c7f5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

seiro-mcp-visionos-build-operator 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 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

| `xcode_unlicensed` | validate | Ask user to accept license (`sudo xcodebuild -license`), then rerun from step 1 |
.agents/skills/seiro-mcp-visionos-build-operator/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

seiro-mcp-visionos-build-operator

Display label: Seiro MCP VisionOS Build Operator

Listing summary: Build and diagnose visionOS projects with Seiro MCP

Purpose

This skill standardizes the operational flow for visionOS builds on Seiro MCP. It does not replace MCP tools. It orchestrates them in a predictable order. Its identifier follows the bundled skill prefix policy: seiro-mcp-.

When to Use / When Not to Use

Use this skill when:

  • The task involves an Xcode project or a visionOS project and requires build, scheme discovery, failure diagnosis, or artifact retrieval.
  • Seiro MCP tools are available and can cover the requested operation.
  • The user explicitly asks to use seiro-mcp-visionos-build-operator.

Do not use this skill when:

  • The task is unrelated to visionOS build operations.
  • The user explicitly asks to run raw shell commands such as xcodebuild or swiftc.
  • Seiro MCP is unavailable or cannot satisfy the requested operation.

Required Inputs

Collect and confirm these inputs before running the flow:

  • project_path (absolute path, allowed by server policy)
  • scheme
  • Optional workspace
  • Optional destination (defaults to Apple Vision Pro simulator destination)
  • Optional configuration
  • Optional extra_args
  • Optional include_logs for artifact fetch

Canonical Flow

  1. Optional project/scheme discovery:
    • If project_path or scheme is missing/unknown, call inspect_xcode_schemes first to discover candidate schemes.
    • Treat .xcodeproj and .xcworkspace as directory packages, not regular files.
    • Do not conclude that the project is missing based only on file-only searches such as rg --files or *.xcodeproj file globs.
    • If local inspection is needed before the MCP call, use directory-aware discovery (for example, find . -maxdepth 1 -type d \\( -name "*.xcodeproj" -o -name "*.xcworkspace" \\)).
    • If project_path is omitted for inspect_xcode_schemes, resolution order is:
      1. .xcodeproj discovered in current working directory
      2. visionos.default_project_path from config.toml

Read the full file on GitHub · 107 lines

Files

What ships with it

3 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 · 107 lines · 86 tokens per session scan B 38a40f2c7f5d

Subscribe to this mod's changes

seiro-mcp-visionos-build-operator is a skill published in the GitHub repository karad/seiro-mcp (16 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 1,408 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.