claude-desktop-to-code: Instructions file for Codex

AGENTS.md

claude-desktop-to-code AGENTS.md is an instructions file for Codex, OpenCode from abhaymettu/claude-desktop-to-code. It costs 1,180 tokens per session, scanned A, original, MIT.

A step-by-step guide for installing claude-desktop-to-code, a macOS tool that connects Claude Desktop with Claude Code. It checks prerequisites, uses an isolated Python environment, and asks for approval before writing changes.

In plain words
What is it for?
Use it when setting up the tool, checking Python and Claude Code, installing it safely, and completing its setup process.
Why use it?
It prevents an installation from proceeding with missing requirements or without showing the user what will happen.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is abhaymettu/claude-desktop-to-code's own configuration. It tells Codex and OpenCode how to work on claude-desktop-to-code itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-desktop-to-code configures →

Reuse

Borrowing it

Nothing to install: this file belongs to abhaymettu/claude-desktop-to-code. 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/abhaymettu/claude-desktop-to-code/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/abhaymettu/claude-desktop-to-code

Made for: Codex, OpenCode.

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.

agentmods badge for claude-desktop-to-code AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/abhaymettu/claude-desktop-to-code/agents-md.svg)](https://agentmods.dev/instructions/abhaymettu/claude-desktop-to-code/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/abhaymettu/claude-desktop-to-code/agents-md"><img src="https://agentmods.dev/badge/instructions/abhaymettu/claude-desktop-to-code/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,180 This file is loaded in full into every session.
When invoked 1,180 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01180 $0.01180
Opus 5 $0.00590 $0.00590
Sonnet 5 $0.00236 $0.00236
Haiku 4.5 $0.00118 $0.00118

Measured 7d ago against content hash ece7cbb7a112, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

claude-desktop-to-code 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 7d 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.

AGENTS.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Installing claude-desktop-to-code

You are an agent installing this for the person you are working with. Follow these steps in order. Stop and ask before step 5, which is the only step that writes anything.

This installs a local MCP server for Claude Desktop. It is macOS only.

The repo is claude-desktop-to-code; the installed command and Python module are both named cc-handoff / cc_handoff. That is expected, not a mistake.

1. Check the prerequisites

python3 --version                  # need 3.10 or newer
command -v claude || echo MISSING  # the Claude Code CLI must be on PATH

Do not use which claude. Many people wrap it in a shell function, and which prints the function body rather than a path, which is easy to misread in both directions. The authoritative check is doctor in step 6.

If claude is missing, stop and tell the user to install Claude Code first. Nothing else here will work without it.

2. Install

git clone https://github.com/abhaymettu/claude-desktop-to-code
cd claude-desktop-to-code
python3 -m venv .venv
.venv/bin/pip install -e .

Use the venv interpreter for every command below. Do not install into system Python.

3. Ask what it would do

.venv/bin/python -m cc_handoff setup --dry-run --json

This writes nothing. It returns the full plan as JSON:

  • profiles, the directories it proposes, each with name, path, gist, exists, and new
  • profile_source, whether these were discovered or kept from a config already present
  • default_profile and default_valid
  • terminal and terminal_tested
  • desktop_config, where Claude Desktop's config lives and whether cc-handoff is in it

If profiles is empty, the user has no directories with a CLAUDE.md. Tell them that a profile is just a directory with its own CLAUDE.md, and that they should create one before continuing.

4. Show the user and get a decision

Do not skip this. Setup writes to their Claude Desktop config and decides which directories become reachable from a chat window.

Read the full file on GitHub · 123 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. 7d ago First seen · 123 lines · 1,180 tokens per session scan A ece7cbb7a112

Subscribe to this mod's changes

claude-desktop-to-code AGENTS.md is an instructions file published in the GitHub repository abhaymettu/claude-desktop-to-code (0 stars, last pushed 16d ago), licensed MIT. It adds 1,180 tokens to every session, about $0.0059 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

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 · 5,153 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

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.

vercel/next.js · 7,296 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 · 4,469 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

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