cowork-to-code-bridge: Instructions file for Claude Code

CLAUDE.md

cowork-to-code-bridge CLAUDE.md is an instructions file for Claude Code from abhinaykrupa/cowork-to-code-bridge. It costs 1,377 tokens per session, scanned A, original, MIT.

A bridge for asynchronous file-based communication between a Cowork sandbox and a local computer. A local daemon runs queued work and returns results through a shared directory.

In plain words
What is it for?
Use it to queue local computer tasks from a Cowork session, exchange files and results, and initialize the bridge when connecting to a machine for the first time.
Why use it?
It lets work started in an isolated sandbox run on the user’s own Mac or Linux machine. Its first-connection setup also loads the bridge’s capabilities and initialization context.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents.

This is abhinaykrupa/cowork-to-code-bridge's own configuration. It tells Claude Code how to work on cowork-to-code-bridge 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 cowork-to-code-bridge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to abhinaykrupa/cowork-to-code-bridge. 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/abhinaykrupa/cowork-to-code-bridge/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/abhinaykrupa/cowork-to-code-bridge

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.

agentmods badge for cowork-to-code-bridge CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/abhinaykrupa/cowork-to-code-bridge/claude-md/github.svg)](https://agentmods.dev/instructions/abhinaykrupa/cowork-to-code-bridge/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/abhinaykrupa/cowork-to-code-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/abhinaykrupa/cowork-to-code-bridge/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.

agentmods 80×15 button for cowork-to-code-bridge CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/abhinaykrupa/cowork-to-code-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/abhinaykrupa/cowork-to-code-bridge/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,377 This file is loaded in full into every session.
When invoked 1,377 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 $0.01377 $0.01377
Opus 5 $0.00688 $0.00688
Sonnet 5 $0.00275 $0.00275
Haiku 4.5 $0.00138 $0.00138

Measured 10d ago against content hash 80adc033d012, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cowork-to-code-bridge 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 10d 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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — cowork-to-code-bridge

Async file-based RPC between a Cowork sandbox and the user's own machine. A Cowork session queues work; a local daemon runs it on the Mac/Linux box and returns results through a shared bind-mounted directory (BRIDGE_ROOT).

First connection — read this

When the bridge client loads, check whether this is a first connection and, if so, read the initialization knowledge base before doing anything else:

from cowork_to_code_bridge.bridge_init import (
    is_first_connection, get_bridge_context,
    get_initialization_message, mark_bridge_initialized,
)

if is_first_connection():
    print(get_initialization_message())  # friendly intro for the user
    print(get_bridge_context())          # load capabilities into context
    mark_bridge_initialized()            # shown once per machine

The full reference is in docs/BRIDGE_INIT.md — and the identical content is available programmatically via get_bridge_context() so it works even when docs/ isn't mounted into the sandbox.

Initialization functions live in cowork_to_code_bridge/bridge_init.py: get_bridge_context(), is_first_connection(), mark_bridge_initialized(), get_initialization_message(). They are agnostic, idempotent, and non-blocking.

Core functions (in cowork_to_code_bridge/client.py)

Function Blocking? Use
call_remote yes run and wait for result
queue_task no fire-and-forget; returns task_id
poll_task_result no (idempotent) check a queued task
cancel_task no (idempotent) stop a queued/running task
post_message_to_cowork no machine → Cowork update
detect_messages_from_claude_code no (idempotent) read those updates

Rule of thumb: if work might take longer than ~30s, queue_task it rather than blocking with call_remote. Pass an idempotency_key for state-changing work so retries don't double-fire.

Read the full file on GitHub · 105 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. 10d ago First seen · 105 lines · 1,377 tokens per session scan A 80adc033d012

Subscribe to this mod's changes

cowork-to-code-bridge CLAUDE.md is an instructions file published in the GitHub repository abhinaykrupa/cowork-to-code-bridge (13 stars, last pushed 5d ago), licensed MIT. It adds 1,377 tokens to every session, about $0.0069 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.

Related

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.

vercel/next.js · 7,296 tokens

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

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

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

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