ciel-mobile-guild

ciel-mobile-guild is an agent for Claude Code from jxoesneon/Ciel. It costs 31 tokens per session (468 once invoked), scanned A, original, Apache-2.0.

A coding-agent guide for building mobile apps and progressive web apps, which are websites that can work like installed apps. It covers Swift, Kotlin, Flutter, React Native, and augmented or virtual reality.

In plain words
What is it for?
Use it when developing iOS or Android apps, cross-platform apps, offline-capable web apps, or AR/VR features.
Why use it?
It gives development work clear priorities for performance, accessibility, safe concurrent code, and keeping sensitive data on the device where possible. It also requires checking platform features with simulator or device logs.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it when developing iOS or Android apps, cross-platform apps, offline-capable web…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jxoesneon/ciel/ciel-mobile-guild
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.

Clone the repo
git clone --depth 1 https://github.com/jxoesneon/Ciel

Made for: Claude Code.

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 ciel-mobile-guild

README.md
[![agentmods](https://agentmods.dev/badge/agents/jxoesneon/ciel/ciel-mobile-guild.svg)](https://agentmods.dev/agents/jxoesneon/ciel/ciel-mobile-guild)
Your own site
<a href="https://agentmods.dev/agents/jxoesneon/ciel/ciel-mobile-guild"><img src="https://agentmods.dev/badge/agents/jxoesneon/ciel/ciel-mobile-guild.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 468 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 $0.00031 $0.00468
Opus 5 $0.00015 $0.00234
Sonnet 5 $0.00006 $0.00094
Haiku 4.5 $0.00003 $0.00047

Measured 6d ago against content hash 85df7be8f3a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ciel-mobile-guild 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 6d 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.

agents/ciel-mobile-guild.md · 40 lines

What it actually says

CIEL GUILD: Mobile & PWA (The Device)

You are CIEL's layer for on-device excellence. You prioritize native performance, data-race safety, and accessibility.

Mandates (CIEL 1.0)

  • Iron Law: Fresh verification (Simulator/Device logs) for all platform features.
  • Concurrency: Swift 6.2 Approachable Concurrency; no data races.
  • Privacy: Local-first processing; PHI/PII MUST stay on the device where possible.

Guild Expertise

  1. iOS: Swift (SwiftUI/Concurrency), Actor-based persistence, and Liquid Glass design.
  2. Android: Kotlin (Compose/Flow), Clean Architecture, and KMP.
  3. Cross-Platform: Flutter (Riverpod/BLoC), React Native, and high-performance PWAs.
  4. Spatial: ARKit, RealityKit, and immersive AR/VR workflows.

Specialist Personas

  • Swift Specialist: Expert in MainActor-first design and FoundationModels on-device LLM.
  • Kotlin Expert: Master of structured concurrency and KMP business logic sharing.
  • Flutter Artist: Building highly performant, visually rich UI across all platforms.
  • PWA Pioneer: Native-quality web apps with offline persistence and service workers.
  • Mobile Architect: Designing modular, testable apps that scale to 1M+ users.

Anti-Patterns

  • Main Thread Blocking: Performing heavy I/O or JSON parsing on the UI thread.
  • Implicit Offloading: Assuming async work runs in the background in Swift 6.2 (it stays on the caller).
  • Hardcoded Pixels: Using fixed values instead of relative scaling and dynamic type.
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. 6d ago First seen · 40 lines · 31 tokens per session scan A 85df7be8f3a7

Subscribe to this mod's changes

ciel-mobile-guild is an agent published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 6d ago), licensed Apache-2.0. It adds 31 tokens to every session and 468 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

mobile

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for mobile application packages (Android APK and iOS IPA static analysis, plus direct testing of the backend endpoints the app reveals).

ASCIT31/Dark-Moon · 39 tokens

mobile_engineer

Mobile engineering specialist for iOS, Android, React Native, and Flutter feature work. Use when the task requires native platform APIs, mobile navigation flows, platform-specific UI patterns, background tasks, or app store compliance. For example: building a push notification handler, wiring biometric auth…

josstei/maestro-orchestrate · 71 tokens

edge-proxy

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for an edge and reverse-proxy tier (Cloudflare/Nginx/HAProxy/Traefik/Envoy/F5-BIG-IP/Citrix-ADC: origin discovery, admin planes, request smuggling, cache poisoning, WAF bypass).

ASCIT31/Dark-Moon · 0 tokens

gitops

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for a GitOps control plane (ArgoCD/FluxCD/Tekton/Crossplane, their controllers, repo and cluster credentials, and the git-to-cluster pivot).

ASCIT31/Dark-Moon · 51 tokens

golang

Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for Go (Gin / Echo / Fiber / Beego / net-http) web applications.

ASCIT31/Dark-Moon · 32 tokens

planner

A planning assistant that reads source material and creates a structured outline for an article, essay, overview, guide, or another requested text type.

mikeshu2001/content-factory · 41 tokens