coclaude: Instructions file for Claude Code

CLAUDE.md

coclaude CLAUDE.md is an instructions file for Claude Code from adechassey/coclaude. It costs 1,169 tokens per session, scanned A, original, MIT.

A project guide for coclaude, a multiplayer Claude Code application where one host runs the coding-agent session and other people join through a live connection. It documents commands, architecture, and where to begin reading the code.

In plain words
What is it for?
Use it to run development, type-checking, and build commands, understand the main session and network files, and follow the documented release workflow.
Why use it?
It gives the agent the project-specific rules and structure needed to make changes safely, including the required checks and release process.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is adechassey/coclaude's own configuration. It tells Claude Code how to work on coclaude 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 coclaude configures →

Reuse

Borrowing it

Nothing to install: this file belongs to adechassey/coclaude. 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/adechassey/coclaude/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/adechassey/coclaude

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 coclaude CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/adechassey/coclaude/claude-md.svg)](https://agentmods.dev/instructions/adechassey/coclaude/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/adechassey/coclaude/claude-md"><img src="https://agentmods.dev/badge/instructions/adechassey/coclaude/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,169 This file is loaded in full into every session.
When invoked 1,169 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 $0.01169 $0.01169
Opus 5 $0.00584 $0.00584
Sonnet 5 $0.00234 $0.00234
Haiku 4.5 $0.00117 $0.00117

Measured 7d ago against content hash 3191c6bc2515, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

coclaude 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 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.

CLAUDE.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 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.

What this is

coclaude is a multiplayer Claude Code application. The host process owns an SDK-driven Claude Code session and exposes a WebSocket server; joiners connect over WS and see / contribute to the same conversation. Design rationale (15 decisions, with the "why" behind each) lives in PLAN.md — read it before architectural changes.

Commands

pnpm dev <subcommand>     # tsx src/cli.ts — e.g. pnpm dev host
pnpm typecheck            # the only correctness gate; no test runner yet
pnpm build                # tsc -p . + chmod +x → ./dist/cli.js

Node 22+. Use pnpm (declared packageManager). No linter beyond tsc --noEmit. Cutting a release: invoke /release (skill at .claude/skills/release/) — don't tag manually, the skill encodes preflight checks you'll miss.

Where to start reading

For a quick map: src/session/SessionView.ts (the interface — ~50 lines, cleanest summary of runtime surface), then src/session/Session.ts (the host's implementation, ~800 lines, the heart of the project), then src/wire/server.ts (the WS bridge).

Architecture

One app, two roles, one TUI. src/tui/App.tsx takes a SessionView and renders identically for host and every joiner. Two implementations: Session (host, owns the SDK call + state) and RemoteSession (joiner, mirrors host state via WS). Add a method to SessionView → both implementations satisfy it, and a wire message may need adding.

One event format, three destinations. Session.emit() is the single fan-out point. A CoEvent (union in src/types.ts) flows to: the on-disk JSONL log at ~/.coclaude/sessions/<id>.jsonl, the in-memory ring (capped at 500), and all subscribed listeners — including the wire forwarder which sends them to joiners. Same format everywhere is load-bearing; don't introduce a separate "wire log" or "audit log" format. Subscribers attach via on() (replays the ring on subscribe) or onFuture() (no replay) — the wire forwarder MUST use onFuture() because joiners already get the snapshot in welcome.

Read the full file on GitHub · 44 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 · 44 lines · 1,169 tokens per session scan A 3191c6bc2515

Subscribe to this mod's changes

coclaude CLAUDE.md is an instructions file published in the GitHub repository adechassey/coclaude (3 stars, last pushed 3mo ago), licensed MIT. It adds 1,169 tokens to every session, about $0.0058 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

vibetags com-example-config-AsyncTestConfig.instructions.md

Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.

PIsberg/vibetags · 82 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 · 5,182 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