What is bed-of-roses CLAUDE.md?

Project instructions for Bed of Roses, an AI-native macOS companion with a desktop presence and a Node-based runtime.

Use them when working on the Bed of Roses browser shell, macOS host, server, onboarding, or related development commands.

They give a coding agent the project's architecture, commands, and development context so changes fit the existing application.

How SixHq/bed-of-roses configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to SixHq/bed-of-roses. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/SixHq/bed-of-roses/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/SixHq/bed-of-roses

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sixhq/bed-of-roses/claude-md/github.svg)](https://agentmods.dev/instructions/sixhq/bed-of-roses/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sixhq/bed-of-roses/claude-md"><img src="https://agentmods.dev/badge/instructions/sixhq/bed-of-roses/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sixhq/bed-of-roses/claude-md"><img src="https://agentmods.dev/badge/instructions/sixhq/bed-of-roses/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,381 This file is loaded in full into every session.

When invoked 4,381 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.04381	$0.04381
Opus 5.5	$0.01752	$0.01752
Sonnet 5.5	$0.00876	$0.00876
Haiku 4.5	$0.00438	$0.00438

Measured 2mo ago against content hash 98ed6af449fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bed-of-roses 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 2mo 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 · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project

Bed of Roses (BOR) — an AI-native macOS companion. A draggable presence lives above the user's real desktop; chat turns produce generated apps, widgets, files, theme changes, or tool calls via an XML protocol.

The repo has two surfaces:

Classic browser shell (shell/ + server/) — original browser-hosted "empty OS" served at http://localhost:7777. Still used for onboarding.
v2 Mac host (host/) — Electron wrapper that owns a frameless always-on-top presence window, opens generated surfaces as native windows, and applies macOS wallpapers. Reuses the same Node runtime under the hood.

See README.md for product framing and HANDOFF-2026-05-20-v2-mac-presence-lifecycle.md for the v2 migration context.

Commands

npm start              # launch BOR: Electron host (spawns the Node runtime itself)
npx bor                # alias of npm start
npm run server         # run just the Node runtime on :7777 (open http://localhost:7777)
npm run server:dev     # same with --watch
npm run browser:install  # install Playwright Chromium for MCP browser automation
npm run browser:mcp    # run the Playwright MCP browser service standalone

No build step, no test suite, no lint config. Node ≥ 20. Runtime dependencies are minimal: electron, @modelcontextprotocol/sdk + @playwright/mcp, croner, and the file-extraction stack ported from Sixth (pdf-parse, mammoth, exceljs, jschardet, iconv-lite, isbinaryfile).

The user's other project at /Users/mac/sixth-vscode-v2 (the "Sixth" AI VSCode extension) is the standing reference implementation — when building or overhauling agent capabilities (tools, file handling, context management, result formatting), scan the corresponding mechanism there first and port the proven approach.

Useful env overrides:

PORT — runtime HTTP port (default 7777)
BOR_RUNTIME_URL=http://127.0.0.1:7777 npm start — attach the host to an already-running runtime instead of spawning one
BOR_BROWSER_HEADLESS=1, BOR_BROWSER_EXECUTABLE_PATH=…, BOR_BROWSER_CHANNEL=chrome — control the user-facing Browser app
BOR_CHAT_MAX_PASSES, BOR_CHAT_STREAM_ATTEMPTS, BOR_TOOL_MAX_ATTEMPTS, BOR_STREAM_IDLE_TIMEOUT_MS — chat loop tuning (see server/ai.js, server/retry.js)

Read the full file on GitHub · 135 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.

2mo ago First seen · 135 lines · 4,381 tokens per session scan A 98ed6af449fa

Subscribe to this mod's changes

bed-of-roses CLAUDE.md is an instructions file published in the GitHub repository SixHq/bed-of-roses (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 4,381 tokens to every session, about $0.0175 per session on Opus 5.5. 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.

agentic-ai ai-agent ai-assistant ai-companion browser-automation claude

bed-of-roses CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bed-of-roses CLAUDE.mdSixHq/bed-of-roses	Instructions file	2	3mo ago	Apache-2.0	A	4,381	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

bed-of-roses: Instructions file for Claude Code