sky-windows-remote-executor AGENTS.md

Repository instructions for Sky Windows Remote Executor, a Windows service that exposes command, file, system, and desktop controls through web and MCP interfaces.

In plain words
What is it for?
Use them when developing or operating the service, including setup, environment configuration, Windows service management, and security-sensitive changes.
Why use it?
They document how to run and configure the service and highlight the need to keep its default local-only security setting.

Instructions file for CodexOpenCode

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/skycaier/sky-windows-remote-executor/agents-md
Clone the repo
git clone --depth 1 https://github.com/skycaier/sky-windows-remote-executor

Made for: Codex, OpenCode.

Per session 584 This file is loaded in full into every session.
When invoked 584 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 $0.00584 $0.00584
Opus 5 $0.00292 $0.00292
Sonnet 5 $0.00117 $0.00117
Haiku 4.5 $0.00058 $0.00058

Measured yesterday against content hash 541f1899762a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sky-windows-remote-executor AGENTS.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 yesterday.

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.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Repository guidance for agentic coding tools.

Project Overview

Sky Windows Remote Executor is a Windows-hosted FastAPI service with REST, WebSocket, Web UI, and MCP /mcp interfaces. The main module is windows_remote_executor.py.

The service is powerful: it can run commands, edit files, manage Windows services, inspect processes, read/write registry values, create scheduled tasks, and interact with the desktop. Keep the default localhost-only security stance unless the user explicitly asks for a trusted remote deployment.

Run

.\venv\Scripts\python.exe -m pip install -r requirements.txt
.\venv\Scripts\python.exe -u windows_remote_executor.py

Batch helpers:

  • start-dev.bat
  • start-silent.bat
  • start-service.bat
  • install-service.bat
  • uninstall-service.bat

Default URL: http://localhost:8765

Configuration

Runtime settings come from environment variables. Important ones:

  • WRE_HOST, default 127.0.0.1
  • WRE_PORT, default 8765
  • WRE_SERVICE_NAME, default SkyWindowsRemoteExecutor
  • WRE_DATA_DIR, default %ProgramData%\SkyWindowsRemoteExecutor
  • WRE_LOG_DIR, WRE_UPLOAD_DIR, WRE_TEMP_DIR

Do not reintroduce machine-specific paths, private IP addresses, passwords, or tokens into tracked files.

Architecture

  • windows_remote_executor.py - main FastAPI app, REST endpoints, WebSockets, MCP JSON-RPC dispatch, task management, transfer tickets, and service helpers.
  • ui_v32.html - vanilla JavaScript Web UI served at /.
  • tools/mcp_schema.py - MCP tool schema list.
  • tools/patch_tools.py - patch, search, and git commit helpers.
  • tools/desktop_tools.py - screenshot, clipboard, notification, lock screen, and event log helpers.
  • tools/_ctx.py - shared runtime context injected by the main module.
  • skills/ - optional Codex skills for clients that want task-specific docs.

Verification

Run before publishing changes:

.\venv\Scripts\python.exe -m unittest discover -s tests -v
$env:PYTHONDONTWRITEBYTECODE = "1"
.\venv\Scripts\python.exe -c "import windows_remote_executor as m; print(m.SETTINGS.app_name, len(m.MCP_TOOLS))"

Read the full file on GitHub · 73 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. yesterday First seen · 73 lines · 584 tokens per session scan A 541f1899762a

Subscribe to this mod's changes

sky-windows-remote-executor AGENTS.md is an instructions file published in the GitHub repository skycaier/sky-windows-remote-executor (1 stars, last pushed 2mo ago), licensed MIT. It adds 584 tokens to every session, about $0.0029 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 instructions, from other repositories

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens