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.
npx agentmods add instructions/ks6573/syscontrol/claude-mdgit clone --depth 1 https://github.com/ks6573/SysControlWhat 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 | $0.04224 | $0.04224 |
| Opus 5 | $0.02112 | $0.02112 |
| Sonnet 5 | $0.00845 | $0.00845 |
| Haiku 4.5 | $0.00422 | $0.00422 |
Grade A, and why
SysControl 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 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.
How it starts
The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — SysControl Project Guide
What is SysControl?
An AI agent for macOS and Windows 11 that answers questions about your system using 116 MCP tools. Four interfaces share the same Python backend: native SwiftUI app (macOS), Flet desktop app (Windows, flet_app/), CLI (cross-platform), and Claude Desktop (MCP server).
Repo: ks6573/SysControl on GitHub.
Cross-platform: the Python backend (agent/, mcp/, deep_research/, flet_app/) and the CLI run on macOS, Windows, and Linux. mcp/server.py branches on IS_MACOS/IS_LINUX/IS_WIN (see the get_startup_items() dispatcher pattern); macOS-only tools (AppleScript: iMessage/Mail/Calendar/Contacts/Notes, Homebrew, Time Machine) return a clean "not supported" dict off macOS rather than failing. The SwiftUI app is macOS-only; the Flet app is the Windows GUI (both drive the same backend).
Architecture
agent.py ← CLI entry shim → agent.cli:main()
mcp/server.py ← MCP server (~9200 lines, all 116 built-in tools, JSON-RPC over stdio)
mcp/connectors.py ← External stdio MCP manager; minimal env + namespaced tool routing
mcp/tool_capabilities.py ← Platform, permission, category, and risk metadata for every tool
mcp/prompt.json ← System prompt injected into all LLM requests
agent/core.py ← Shared: MCPClient, MCPClientPool, run_streaming_turn(), TurnCallbacks
agent/bridge.py ← JSON-over-stdio bridge for the Swift frontend
agent/cli.py ← Interactive terminal agent (prompt_toolkit REPL, slash registry, /show, /init, /compact, --continue/--resume)
agent/cli_keys.py ← KeyBindings (Enter/Ctrl-D submit semantics) + SIGINT install_sigint_handler context manager
agent/cli_completers.py← _SlashCompleter merge target + AtFileCompleter; submit-time @file expansion
agent/cli_session.py ← Atomic JSON session store at ~/.syscontrol/cli_sessions/
agent/cli_compact.py ← Synchronous /compact summarization with undo snapshot
agent/credentials.py ← Native Keychain/Credential Manager storage with protected-file fallback
agent/automations.py ← Persistent bounded scheduler + run history for read-only tool automations
agent/audit.py ← Privacy-preserving JSONL audit log (argument names, never values)
agent/updater.py ← `syscontrol --update` / `/update` self-update via uv tool install
agent/slash.py ← SlashCommand dataclass + SlashRegistry consumed by cli.py
agent/agents.py ← Sub-agent specs: AgentSpec, AgentRegistry, 5 built-in agents
agent/runner.py ← Sub-agent runner: run_subagent() with isolated context + filtered tools
deep_research/ ← Deep research agent: iterative web research with claim verification
flet_app/ ← Native Windows desktop GUI (Flet, Python) — Windows counterpart to swift/
main.py ← Entry + frozen-bundle argv sentinel (--run-mcp-server / --selftest)
app.py, controller.py← Page assembly + central orchestration; runs the backend in-process
backend.py ← run_streaming_turn() on a worker thread (no subprocess bridge needed)
callbacks via controller; views/ (chat, sidebar, settings, onboarding), store/ (~/.syscontrol JSON)
scripts/make_icon.py ← Generates .icns app icon from source image
swift/ ← Native SwiftUI macOS app (macOS 14+)
SysControl/
App/ ← SysControlApp.swift (entry), AppState.swift (central @Observable)
Services/ ← BackendService.swift (bridge IPC), UpdateService.swift
Views/ ← SwiftUI views (Chat, Sidebar, Settings, InputBar, etc.)
Models/ ← ChatMessage, ChatSession, ProviderConfiguration, SavedChat
Storage/ ← PersistenceManager, ChatHistoryManager, ProviderConfigStore, PermissionConfigStore
Package.swift ← SPM manifest — explicit source list, must be updated when adding files
build.sh ← Builds .app bundle + optional .dmg (reads VERSION → Info.plist)
install.sh ← One-liner installer: clone, build, install to /Applications
VERSION ← Single source of truth for app version
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.
- yesterday First seen · 273 lines · 4,224 tokens per session scan A 251001afe441
SysControl CLAUDE.md is an instructions file published in the GitHub repository ks6573/SysControl (0 stars, last pushed 1mo ago), licensed MIT. It adds 4,224 tokens to every session, about $0.0211 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
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.
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).
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.
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).
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.