Borrowing it
Nothing to install: this file belongs to isac322/kwin-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/isac322/kwin-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/isac322/kwin-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/isac322/kwin-mcp/claude-md)<a href="https://agentmods.dev/instructions/isac322/kwin-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/isac322/kwin-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 | $0.02458 | $0.02458 |
| Opus 5 | $0.01229 | $0.01229 |
| Sonnet 5 | $0.00492 | $0.00492 |
| Haiku 4.5 | $0.00246 | $0.00246 |
Grade A, and why
kwin-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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Working Guidelines
Project Overview
kwin-mcp is an MCP (Model Context Protocol) server for Linux desktop GUI automation on KDE Plasma 6 Wayland. Purpose: Enable AI agents (Claude Code and other MCP clients) to launch, interact with, and observe any Wayland application — either in a fully isolated virtual KWin session for reproducible GUI testing, or by connecting to a live KDE Plasma desktop (real session or container) for collaborative desktop automation workflows.
Toolchain
- Package Manager:
uv(Astral). Always use uv instead of pip/poetry. - Lint + Format:
ruff(Astral). Config inpyproject.tomlunder[tool.ruff]. - Type Check:
ty(Astral). Config inpyproject.tomlunder[tool.ty]. - Build:
uv build(uv_build backend)
Common Commands
uv sync # Install/sync dependencies
uv add <pkg> # Add dependency
uv add --dev <pkg> # Add dev dependency
uv run ruff check . # Lint
uv run ruff format . # Format
uv run ty check # Type check
uv run python -m kwin_mcp # Run server
Code Style
- Python 3.12+
- ruff rules: E, F, W, I, N, UP, B, A, SIM, TCH, RUF
- Line length: 100
- Quotes: double quote
- Type hints required
- All documents (.md files), code comments, and docstrings must be written in English
Architecture
See ROADMAP.md. Key modules:
core.py: AutomationEngine — MCP-independent automation logic (session, input, screenshot, a11y)server.py: Thin MCP wrappers delegating to AutomationEnginecli.py: Interactive REPL + pipe mode viacmd.Cmd(kwin-mcp-clientry point)session.py: Virtual sessions (dbus-run-session + kwin_wayland --virtual) and live session attachment (session_connect to real desktop or container)screenshot.py: KWin ScreenShot2 D-Bus (screenshots)accessibility.py: AT-SPI2 (widget tree)input.py: KWin EIS D-Bus + libei (input injection)
Pre-work Checklist
- Read
ROADMAP.mdto understand current progress - Start from the first incomplete item in the next milestone
- After code changes, run
uv run ruff check .+uv run ruff format .+uv run ty check - Update ROADMAP.md checklist when a milestone item is completed
- Verify with CLI, not MCP tools: After modifying any kwin-mcp code, verify via the CLI (
uv run python -m kwin_mcp.cli), NOT the MCP server tools. The MCP server process is already running with the old code loaded in memory — calling MCP tools after editing source files will NOT reflect the changes. Use the CLI to launch a session and test the modified functionality. Usekeep_screenshots=trueinsession_startto preserve screenshot files aftersession_stop(they are deleted by default). Files in/tmp/kwin-mcp-screenshots-*must be cleaned up manually when this option is used. - Invoke docs-seo agent after relevant file changes: After modifying any of the trigger files below, invoke the
@docs-seoagent to evaluate whether documentation is stale. A no-op conclusion is acceptable if nothing needs updating.
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 · 140 lines · 2,458 tokens per session scan A b9753cfe2b43
kwin-mcp CLAUDE.md is an instructions file published in the GitHub repository isac322/kwin-mcp (43 stars, last pushed 1mo ago), licensed MIT. It adds 2,458 tokens to every session, about $0.0123 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 2026-08-30.
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).
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.
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.