agentmods.dev

stealth-code CLAUDE.md

Repository instructions for StealthCode, a Windows desktop app that runs AI coding command-line tools in a secure terminal window hidden from screen capture.

In plain words
What is it for?
Building, running, publishing, and modifying the StealthCode application and its terminal, screen-capture, and audio-capture components.
Why use it?
They explain the project's build commands, architecture, platform limits, and coding conventions before development work begins.

Instructions file

3 2d ago A scan 692 tokens original MIT
View the source file suxrobGM/stealth-code
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/suxrobgm/stealth-code/claude-md
Clone the repo
git clone --depth 1 https://github.com/suxrobGM/stealth-code
Per session 692 This file is loaded in full into every session.
When invoked 692 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00692 $0.00692
Opus 5 $0.00346 $0.00346
Sonnet 5 $0.00138 $0.00138
Haiku 4.5 $0.00069 $0.00069

Measured 2d ago against content hash b898d1a432ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stealth-code 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.

CLAUDE.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

StealthCode

A Windows desktop app (Avalonia UI) that runs AI coding CLIs (Claude Code, Codex, Gemini CLI) in a secure, transparent, always-on-top terminal window invisible to screen capture.

Build & Run

dotnet build src/StealthCode/StealthCode.csproj
dotnet run --project src/StealthCode/StealthCode.csproj

Publish single executable (via Launcher):

cd scripts
.\publish.ps1

No test projects exist yet.

Architecture

  • Framework: .NET 10, Avalonia 12.1, PublishAot, full trim
  • Platform: Windows only
  • Pattern: MVVM with CommunityToolkit.Mvvm (source generators)
  • DI: Module registrar pattern — services.AddTerminal(), services.AddScreenCapture(), services.AddAudioCapture(). Stateful services are singletons. Stateless services are static classes.
  • Messaging: WeakReferenceMessenger with explicit Register<T> (no RegisterAll — AOT incompatible)
  • Terminal: xterm.js in NativeWebView (WebView2), bridged via ConPTY

Project Structure

src/
  StealthCode/                  # Main UI app (composition root, MVVM, orchestrators)
  StealthCode.Terminal/         # PTY library (ConPTY via Quick.PtyNet)
  StealthCode.ScreenCapture/    # Win32 screen capture (GDI BitBlt/PrintWindow, PngWriter)
  StealthCode.Audio/            # WASAPI loopback capture (Win32 interop) + Whisper.net transcription
  StealthCode.Updater/          # GitHub release checker + self-update downloader
  StealthCode.Launcher/         # Self-extracting AOT launcher
scripts/
  publish.ps1                   # Build + package pipeline

Modules (Terminal, ScreenCapture, Audio) are independent — zero inter-module dependencies. Orchestrator services (CaptureInjectorService, AudioInjectorService) live in the main app and bridge modules with the terminal.

Key Conventions

  • File-scoped namespaces, braces required
  • [ObservableProperty] for bindable properties, [RelayCommand] for commands
  • Private fields: camelCase. Consts/statics: PascalCase
  • Win32 interop uses [LibraryImport] with partial static classes
  • All colors in Themes/Theme.axaml, all styles in Themes/Styles.axaml
  • Reusable XAML classes: Button.chrome, Button.chrome.pinned, TextBlock.section-header, TextBlock.field-label, Border.divider, *.form-input
  • Settings, models, and captures stored in %APPDATA%/StealthCode/ via System.Text.Json source gen
  • Code-behind kept minimal — only platform-specific ops
  • Content protection disabled in DEBUG builds

Read the full file on GitHub · 61 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 · 61 lines · 692 tokens per session scan A b898d1a432ea

Subscribe to this mod's changes

stealth-code CLAUDE.md is an instructions file published in the GitHub repository suxrobGM/stealth-code (3 stars, last pushed 2d ago), licensed MIT. It adds 692 tokens to every session, about $0.0035 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.

Creative and mediaPlanningavaloniaclaude-codecodexdotnetgemini-cliterminal
Related

Other instructions, from other repositories

codex-provider-sync AGENTS.md

Instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.

Dailin521/codex-provider-sync · 1,480 tokens

hex1b AGENTS.md

Instructions for mitchdenny/hex1b, covering ai coding agent guidelines for hex1b, 🛠️ available skills, 📋 project overview, key technologies and repository layout.

mitchdenny/hex1b · 3,232 tokens

mcp-server-powerpoint architecture-patterns.instructions.md

Instructions for sbroenne/mcp-server-powerpoint, covering architecture patterns, .net class design (mandatory), layered architecture (critical), command pattern and structure (per domain).

sbroenne/mcp-server-powerpoint · 1,597 tokens

research-cli AGENTS.md

Instructions for rmedranollamas/research-cli, covering agent notes, architecture, gemini cli extension, security notes and development.

rmedranollamas/research-cli · 549 tokens

kmux AGENTS.md

Instructions for kkd927/kmux, covering agents.md, kmux focus and test discipline.

kkd927/kmux · 324 tokens

scriveno AGENTS.md

Instructions for hannsxpeter/scriveno, covering project, constraints, technology stack, architecture constraint and recommended stack.

hannsxpeter/scriveno · 4,411 tokens