glass CLAUDE.md

Repository instructions for Claude Code when working in the public Glass Rust workspace. Glass is an MCP server that lets an AI agent launch, inspect, control, and debug native desktop and mobile apps.

In plain words
What is it for?
Use them when changing Glass, including its Rust code, platform backends, app capture and input handling, logs, accessibility support, or MCP setup.
Why use it?
They keep the agent aligned with the project’s layout, commands, rules, and privacy boundaries. They also explain which internal business and security information must stay out of the public repository.

Instructions file

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.

agentmods
npx agentmods add instructions/fixed-width/glass/claude-md
Clone the repo
git clone --depth 1 https://github.com/fixed-width/glass
Per session 1,052 This file is loaded in full into every session.
When invoked 1,052 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 89% copy Near-identical to another mod 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 $0.01052 $0.01052
Opus 5 $0.00526 $0.00526
Sonnet 5 $0.00210 $0.00210
Haiku 4.5 $0.00105 $0.00105

Measured 2d ago against content hash b10ff6cd8e19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

glass 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 2d 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.

Origin

This is a copy

89% identical to glass AGENTS.md — 15 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code working in the glass open-core Rust workspace.

This repository is PUBLIC. Keep internal business/strategy, licensing-strategy framing, planning and design specs, and the internal security threat model out of this repo — that material lives in the private fixed-width repo. Document what the product does, never why it helps the business.

What glass is

A Rust MCP server giving an AI agent a closed build → see → interact → debug loop over external native GUI apps: launch, capture (lossless WebP), inject mouse/keyboard, read logs, diff against baselines, wait-until-stable, and read/drive the accessibility tree — served over MCP (stdio, or serve --http). Backends behind a Platform seam: X11 and Wayland (headless sway) on Linux, Windows (WGC/SendInput), Android (native apps in an AVD emulator over adb, host-OS-agnostic; clipboard + high-fidelity input via an optional on-device companion agent), iOS (native apps in the Simulator over xcrun simctl; capture, logs, clipboard, plus input and the accessibility tree via idb_companion, including a two-finger pinch; other multi-touch gestures excepted), macOS (ScreenCaptureKit capture, CGEvent input, AXUIElement windows/logs, accessibility tree, clipboard (isolated + working under containment for apps not built with hardened runtime, via a DYLD_INSERT_LIBRARIES swizzle shim; hardened-runtime apps fall back to unsupported), sandboxing (Seatbelt)).

Layout

Cargo workspace at the repo root. Crates: glass-core (platform-agnostic heart — the Platform/Accessibility seams, session, Frame, diff, stability, log buffer), the backends (glass-x11, glass-wayland, glass-windows, glass-android, glass-ios (the iOS Simulator backend over xcrun simctl), glass-macos), the a11y readers (glass-a11y-linux, glass-a11y-windows, glass-a11y-macos; the Android uiautomator reader lives in glass-android), glass-sandbox-linux, glass-sandbox-macos, the glass-mcp server binary, and the glass-testapp fixture. glass-android also holds the host-side client + lifecycle for two optional on-device companions — an app_process agent (clipboard + high-fidelity input) and an AccessibilityService (Compose-rich a11y tree + high-fidelity set_value); both live in the separate repo github.com/fixed-width/glass-android-agent, driven over adb forward.

Read the full file on GitHub · 71 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. 2d ago First seen · 71 lines · 1,052 tokens per session scan A b10ff6cd8e19

Subscribe to this mod's changes

glass CLAUDE.md is an instructions file published in the GitHub repository fixed-width/glass (12 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,052 tokens to every session, about $0.0053 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to glass AGENTS.md, differing in 15 lines, and is treated as a copy.

Related

Other instructions, from other repositories

unity-cross-platform-local-build-orchestrator AGENTS.md

Instructions for sinanata/unity-cross-platform-local-build-orchestrator, covering agents.md, what this project is, golden rules (do not violate), use it and interface.

sinanata/unity-cross-platform-local-build-orchestrator · 2,557 tokens

flutter-agentic-starter CLAUDE.md

Instructions for tsnAnh/flutter-agentic-starter, covering claude.md, role & responsibilities, workflows, karpathy guidelines and hard development rules.

tsnAnh/flutter-agentic-starter · 2,054 tokens

unity-cross-platform-local-build-orchestrator copilot-instructions.md

Instructions for sinanata/unity-cross-platform-local-build-orchestrator: This repository follows the cross-tool AGENTS.md standard. Read /AGENTS.md for the full guide: the script/CLI interface, the config workflow, and the operating rules.

sinanata/unity-cross-platform-local-build-orchestrator · 463 tokens

flutter-agentic-starter AGENTS.md

Instructions for tsnAnh/flutter-agentic-starter, covering agents.md, project overview, role & responsibilities, workflows and development principles.

tsnAnh/flutter-agentic-starter · 1,661 tokens

xtool CLAUDE.md

Instructions for 2389-research/xtool, covering xtool plugin, skills included, using-xtool (main skill), key patterns and xtool is not xcodegen.

2389-research/xtool · 525 tokens

alliswell AGENTS.md

AGENTS.md instructions for mahirozdin/alliswell, covering agents.md — operating manual for ai agents (and humans), 1. hard rules (non-negotiable), 2. the "do the next task" protocol, 3. definition of done (checklist) and 4. code conventions.

mahirozdin/alliswell · 2,804 tokens