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/omarshahine/homeclaw/agents-mdgit clone --depth 1 https://github.com/omarshahine/HomeClawWrote 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/omarshahine/homeclaw/agents-md)<a href="https://agentmods.dev/instructions/omarshahine/homeclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/omarshahine/homeclaw/agents-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 | $0.10109 | $0.10109 |
| Opus 5 | $0.05054 | $0.05054 |
| Sonnet 5 | $0.02022 | $0.02022 |
| Haiku 4.5 | $0.01011 | $0.01011 |
Grade A, and why
HomeClaw 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 today.
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 — 719 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HomeClaw
HomeClaw exposes Apple HomeKit accessories via a CLI tool, plugins for Claude Code and OpenClaw, and a stdio MCP server for Claude Desktop. It uses a unified Mac Catalyst architecture with an AppKit bridge bundle for the macOS menu bar.
Architecture
Claude Code → Plugin (.claude-plugin/) → stdio MCP server (Node.js) ─┐
Claude Desktop → stdio MCP server (Node.js) ─────────────────────────┤
OpenClaw → Plugin (openclaw/) → homeclaw-cli ────────────────────────┤
▼
/tmp/homeclaw.sock (JSON newline-delimited)
│
HomeClaw (Mac Catalyst UIKit app)
├── HomeKitManager (direct, in-process)
├── SocketServer (for CLI/MCP clients)
└── macOSBridge.bundle (NSStatusItem menu bar)
Single-process design. HMHomeManager requires a UIKit/Catalyst app with the HomeKit entitlement. By making the entire app Catalyst, HomeKit access is direct (no IPC), signing is unified (single archive), and App Store submission is clean. The macOSBridge plugin bundle provides the native macOS menu bar via NSStatusItem.
Note: The HTTP MCP server (port 9090, bearer token auth) has been disabled. The implementation is preserved in Sources/homeclaw/MCP/_disabled/ and Sources/homeclaw/Shared/_disabled/ for reference but is not compiled. All MCP clients now use the stdio server or CLI.
Project Structure
Sources/
homeclaw/ # Unified Catalyst app (Xcode target via XcodeGen)
App/ # UIApplicationDelegate entry point, scene delegates
Bridge/ # BridgeProtocols.swift (Mac2iOS, iOS2Mac)
MCP/_disabled/ # Preserved HTTP MCP server code (not compiled)
HomeKit/ # HomeKitManager, SocketServer, CharacteristicMapper,
# AccessoryModel, DeviceMap, CharacteristicCache,
# HomeEventLogger, WebhookCircuitBreaker
Views/ # SettingsView, IntegrationsSettingsView
Shared/ # AppConfig, AppLogger, HomeClawConfig
Shared/_disabled/ # Preserved KeychainManager (not compiled)
macOSBridge/ # AppKit bundle (NSStatusItem menu bar)
MacOSController.swift # NSStatusItem + NSMenu
Info.plist # NSPrincipalClass: MacOSController
homeclaw-cli/ # CLI tool (SPM executable + Xcode target)
Commands/ # list, get, set, search, scenes, automations, status, config, device-map
Commands/_disabled/ # Preserved token command (not compiled)
SocketClient.swift # Direct socket communication
Resources/ # Info.plist, entitlements, app icons
scripts/build.sh # Build & install script (debug/release for local use)
fastlane/Fastfile # Release pipeline: archive, upload, beta (TestFlight)
mcp-server/ # Node.js stdio MCP server (wraps homeclaw-cli)
openclaw/ # HomeClaw — OpenClaw plugin
openclaw.plugin.json # Plugin manifest (configurable binDir)
src/index.ts # Plugin entry point
skills/homekit/ # HomeKit skill definition
App bundle layout (after build):
Contents/MacOS/HomeClaw # Catalyst app executable
Contents/MacOS/homeclaw-cli # Bundled CLI binary
Contents/Resources/macOSBridge.bundle # AppKit menu bar plugin
Contents/Resources/mcp-server.js # Node.js stdio MCP server
Contents/Resources/openclaw/ # Bundled OpenClaw plugin files
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.
- today Changed · +5 lines · +65 tokens per session 73c480281190
- 5d ago First seen · 714 lines · 10,044 tokens per session scan A 7607f8730f0b
HomeClaw AGENTS.md is an instructions file published in the GitHub repository omarshahine/HomeClaw (164 stars, last pushed 3d ago), licensed MIT. It adds 10,109 tokens to every session, about $0.0505 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
Peekaboo AGENTS.md
AGENTS.md instructions for openclaw/Peekaboo, covering repository guidelines, start here, project structure & modules, build, test, and development commands and coding style & naming conventions.
Applite CLAUDE.md
Instructions for milanvarady/Applite, covering claude.md, project overview, build & run, architecture and data flow.
palmier-pro AGENTS.md
AGENTS.md instructions for palmier-io/palmier-pro, covering palmierpro, build, agents, engineering approach and code style.
scarf AGENTS.md
Instructions for awizemann/scarf: This repo carries its own agent memory — plain files in git, served by the in-repo memophant-mcp MCP server, managed by the Memophant macOS app. It works the same for every agent (Claude Code, Codex, Cursor, Gemini, Copilot). This block is regenerated between the memophant markers…
scarf copilot-instructions.md
Instructions for awizemann/scarf: File memory notes under one of six folders (architecture/conventions/decisions/operations/project/roadmap), never the root. When a note is grounded in code, pass sourcepaths (the repo files it depends on) so Memory Health can drift-check it — an unanchored code note can't be kept…
liney AGENTS.md
AGENTS.md instructions for everettjf/liney, covering liney repository collaboration guide, 交流语言 / communication language, project overview, repository layout and build and test.