Borrowing it
Nothing to install: this file belongs to MarshallBear1/touchbridge-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MarshallBear1/touchbridge-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/MarshallBear1/touchbridge-mcpWrote 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.
[](https://agentmods.dev/instructions/marshallbear1/touchbridge-mcp/claude-md)<a href="https://agentmods.dev/instructions/marshallbear1/touchbridge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/marshallbear1/touchbridge-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00443 | $0.00443 |
| Opus 5 | $0.00221 | $0.00221 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
touchbridge-mcp 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 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.
What it actually says
TouchBridge
MCP server for controlling iOS simulators and physical iPhones.
Workflow
- Call
get_execution_contextfirst to discover available devices - If setup or connectivity is unclear, call
doctorfor structured read-only diagnostics - If
target === 'ambiguous', ask the user which device to use - If
target === 'device', inform the user aboutviewer_urlso they can see the screen - If
target === 'none', tell the user to boot a simulator or connect an iPhone - Pass the returned
udidto all subsequent tool calls
Key Patterns
- Use
scan_uibefore interacting — it returns interactive elements with tap coordinates - Use
get_screenshotto visually verify the current screen state; its pixels are unredacted, so delete the returned temporary file after use - Use
capture_design_snapshotwhen the screenshot must be durable or handed to Figma, Slides, or another editing tool; pass the user's spoken instruction inintentand consume the returnededitor.jsonfor normalized layers - Use
describe_screenfor the full element tree (all types, not just interactive) - All coordinates are in device screen points (not pixels)
- Use
device_actionsfor batching multiple sequential actions - Choose the smallest
scan_uiregion possible for speed
Physical Devices
- Physical devices require WebDriverAgent (WDA) running on the device
- Run
npx -y github:MarshallBear1/touchbridge-mcp --setupto install WDA and dependencies - The viewer URL shows a live screen stream in the browser
- The agent cannot see the physical device screen directly — rely on
scan_uiandget_screenshot
Coordinate Systems
Common iPhone screen sizes (in points):
- iPhone 15/16 Pro: 393 x 852
- iPhone 15/16 Pro Max: 430 x 932
- iPhone SE: 375 x 667
All coordinates passed to tap/swipe should be in these point values.
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.
- 6d ago First seen · 39 lines · 443 tokens per session scan A 2f1b99943332
touchbridge-mcp CLAUDE.md is an instructions file published in the GitHub repository MarshallBear1/touchbridge-mcp (4 stars, last pushed 13d ago), licensed MIT. It adds 443 tokens to every session, about $0.0022 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.