What is cc-dm CLAUDE.md?

Project instructions for cc-dm, a Claude Code plugin that lets active coding sessions send messages to one another on the same computer.

Working on the plugin's Bun and TypeScript code, including its SQLite message bus, session tracking, permission handling, and heartbeat system.

They give the coding agent the project's runtime, architecture, messaging tools, and rules to follow when changing the code.

How Akram012388/cc-dm configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Akram012388/cc-dm. 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/Akram012388/cc-dm/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Akram012388/cc-dm

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/akram012388/cc-dm/claude-md.svg)](https://agentmods.dev/instructions/akram012388/cc-dm/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/akram012388/cc-dm/claude-md"><img src="https://agentmods.dev/badge/instructions/akram012388/cc-dm/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,521 This file is loaded in full into every session.

When invoked 2,521 The same file — it is already loaded in full.

Security scan C 2 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	$0.02521	$0.02521
Opus 5	$0.01260	$0.01260
Sonnet 5	$0.00504	$0.00504
Haiku 4.5	$0.00252	$0.00252

Measured 8d ago against content hash a27afd89b07d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

cc-dm CLAUDE.md scanned grade C with 2 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 8d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

install.sh curl | bash installer

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

install.sh curl | bash installer

CLAUDE.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

cc-dm is a Claude Code Channel plugin that enables direct peer-to-peer messaging between active Claude Code sessions on the same machine via a shared SQLite bus.

Stack

Runtime: Bun — never use node to run anything in this project
Language: TypeScript, strict mode
MCP SDK: @modelcontextprotocol/sdk
Database: bun:sqlite (built-in, zero external deps)
Channel protocol ref: https://code.claude.com/docs/en/channels-reference

Architecture

.claude-plugin/plugin.json       Plugin manifest + inline mcpServers config
.claude-plugin/marketplace.json  GitHub-hosted marketplace definition
.claude-plugin/hooks/hooks.json  PreCompact hook for compaction identity recovery
src/bus.ts                       SQLite WAL bus, sessions + messages tables
src/tools.ts                     Four tool handlers: dm, who, register, broadcast
src/permission.ts                Pure functions for permission relay: VERDICT_RE, parseVerdict, formatPermissionRequest
src/sanitize.ts                  Shared string sanitizer (trim, lowercase, spaces→hyphens)
src/heartbeat.ts                 30s heartbeat writer, 60s session expiry + 15s message expiry, ghost self-heal
src/server.ts                    MCP entry point, claude/channel capability, permission relay, poll loop, shutdown
skills/cc-dm/SKILL.md            Skill for natural language usage
skills/register/SKILL.md         Interactive session registration skill
tests/                           Unit + integration tests (140 tests, bun:test)
CHANGELOG.md                     Version history
LICENSE                          MIT license
install.sh                       curl | bash installer

Key implementation details

Channel capability declared via:

capabilities.experimental['claude/channel']: {}
capabilities.experimental['claude/channel/permission']: {}  // opt-in, gated on CC_DM_PERMISSION_RELAY=1

SDK notification type extended via Server<never, ChannelNotification | PermissionVerdict> generic to support notifications/claude/channel (messaging) and notifications/claude/channel/permission (verdict relay) methods.

Read the full file on GitHub · 108 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.

8d ago First seen · 108 lines · 2,521 tokens per session scan C a27afd89b07d

Subscribe to this mod's changes

cc-dm CLAUDE.md is an instructions file published in the GitHub repository Akram012388/cc-dm (22 stars, last pushed 5mo ago), licensed MIT. It adds 2,521 tokens to every session, about $0.0126 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

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

cc-dm: Instructions file for Claude Code