What is capacitor-mobile-claw CLAUDE.md?

Repository instructions for capacitor-mobile-claw, a Capacitor plugin that runs an AI agent inside Android and iOS apps.

Use them when building, type-checking, testing, or modifying the plugin, its mobile agent engine, MCP support, or example app.

They explain how the TypeScript plugin, mobile networking, agent runtime, message bridge, and tests fit together.

How sernnee/capacitor-mobile-claw configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sernnee/capacitor-mobile-claw. 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/sernnee/capacitor-mobile-claw/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/sernnee/capacitor-mobile-claw

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sernnee/capacitor-mobile-claw/claude-md/github.svg)](https://agentmods.dev/instructions/sernnee/capacitor-mobile-claw/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sernnee/capacitor-mobile-claw/claude-md"><img src="https://agentmods.dev/badge/instructions/sernnee/capacitor-mobile-claw/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sernnee/capacitor-mobile-claw/claude-md"><img src="https://agentmods.dev/badge/instructions/sernnee/capacitor-mobile-claw/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 567 This file is loaded in full into every session.

When invoked 567 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00567	$0.00567
Opus 5.5	$0.00227	$0.00227
Sonnet 5.5	$0.00113	$0.00113
Haiku 4.5	$0.00057	$0.00057

Measured 2mo ago against content hash b0a2e23c80aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

capacitor-mobile-claw CLAUDE.md 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 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.

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.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — AI-Assisted Development Context

This file provides context for AI coding assistants working on this codebase.

Project Overview

Mobile Claw is a Capacitor plugin (capacitor-mobile-claw) that embeds a full AI agent runtime on Android/iOS. The agent loop runs directly in the WebView — no embedded Node.js worker. LLM API calls are routed through native HTTP (OkHttp / URLSession) to bypass CORS. The agent uses the Pi framework by Mario Zechner.

Repository Structure

src/                    # TypeScript plugin source → compiled to dist/esm/
  engine.ts             # MobileClawEngine — the core public API class
  definitions.ts        # All TypeScript interfaces and event types
  plugin.ts             # Capacitor WebPlugin wrapper
  services/             # Bridge protocol message types
  mcp/                  # MCP server, transports, and tool types
examples/reference-app/ # Vue 3 demo app (private, not published)
test/e2e/               # E2E test files
docs/                   # Extended documentation

Build & Test Commands

npm install             # Install dependencies
npm run build           # TypeScript → dist/esm/
npm run typecheck       # tsc --noEmit
npm test                # Vitest unit tests
npm run test:e2e        # E2E tests (needs ANTHROPIC_API_KEY)
npm run lint            # Biome check
npm run lint:fix        # Biome auto-fix

Key Architecture

Agent loop: Runs in WebView, not a separate worker process
Native HTTP: OkHttp (Android) / URLSession (iOS) bypass CORS for LLM API calls
MCP transports: Bridge (in-process IPC, default) and STOMP (remote WebSocket, opt-in)
Pi framework: @mariozechner/pi-ai and @mariozechner/pi-agent-core power the agent loop

Coding Conventions

TypeScript strict mode, ES2022 target, ESNext modules
No semicolons, single quotes, trailing commas
2 spaces indentation, 120 char line width
Biome for linting and formatting
Conventional commits with scopes: engine, mcp, tools, app, docs, ci, deps

Read the full file on GitHub · 58 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.

2mo ago First seen · 58 lines · 567 tokens per session scan A b0a2e23c80aa

Subscribe to this mod's changes

capacitor-mobile-claw CLAUDE.md is an instructions file published in the GitHub repository sernnee/capacitor-mobile-claw (7 stars, last pushed 1mo ago), licensed MIT. It adds 567 tokens to every session, about $0.0023 per session on Opus 5.5. 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.

Mobile ai ai-agent android anthropic capacitor capacitor-plugin

capacitor-mobile-claw CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
capacitor-mobile-claw CLAUDE.mdsernnee/capacitor-mobile-claw	Instructions file	7	1mo ago	MIT	A	567	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	279k	today	MIT	A	4,325	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

capacitor-mobile-claw: Instructions file for Claude Code