multi-clone-code CLAUDE.md

Instructions for a shell-based tool that coordinates multiple Claude Code sessions across local tmux panes and remote SSH hosts. tmux is a terminal tool for running several sessions, while SSH connects to remote computers.

In plain words
What is it for?
Use it when changing the orchestrator, its YAML session registry, briefing prompts, shared context, synchronization runs, or cross-project summaries.
Why use it?
It provides the project’s layout, session configuration, communication method, and rules for coordinating work without background services or message brokers.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/maflot/multi-clone-code/claude-md
Clone the repo
git clone --depth 1 https://github.com/maflot/multi-clone-code
Per session 363 This file is loaded in full into every session.
When invoked 363 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00363 $0.00363
Opus 5 $0.00181 $0.00181
Sonnet 5 $0.00073 $0.00073
Haiku 4.5 $0.00036 $0.00036

Measured yesterday against content hash 3471c3591b29, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

multi-clone-code 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 yesterday.

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 · 32 lines

What it actually says

Multi-Claude Orchestra

Shell-based orchestrator for managing multiple Claude Code sessions across local tmux panes and remote SSH hosts.

Architecture

  • orchestra.sh — Main CLI. All commands dispatch through here.
  • config.yaml — Session registry (hosts, paths, tmux names, roles, dependencies).
  • prompts/ — Briefing templates (insight.md, dream.md, custom/).
  • shared/CONTEXT.md — Auto-generated global state, updated by orchestra sync.
  • runs/ — Timestamped sync outputs.
  • summary/ — Latest cross-project summary.
  • briefings/ — Logged briefings sent to sessions.

Key Design Decisions

  • No daemons or message brokers. Everything is tmux + SSH ControlMaster + shared filesystem.
  • Python3 for YAML parsing only. The rest is pure bash.
  • SSH ControlMaster sockets live in ~/.ssh/sockets/. User authenticates once interactively, orchestrator rides the socket. Sessions use ControlPersist=4h.
  • Health detection via tmux capture-pane + pattern matching on last N lines.
  • claude -p (print mode) is used for non-interactive insight collection during sync.
  • tmux send-keys is used for interactive briefings to running sessions.

Working on This Repo

  • Test config parsing: ./orchestra.sh status (with example sessions uncommented).
  • All session commands accept a session name or all.
  • When adding new commands, follow the cmd_<name> pattern and register in main().
  • Health check patterns may need tuning for different Claude Code versions.
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. yesterday First seen · 32 lines · 363 tokens per session scan A 3471c3591b29

Subscribe to this mod's changes

multi-clone-code CLAUDE.md is an instructions file published in the GitHub repository maflot/multi-clone-code (2 stars, last pushed 5mo ago), licensed MIT. It adds 363 tokens to every session, about $0.0018 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

operator CLAUDE.md

Instructions for untra/operator, covering claude.md - operator, project overview, tech stack, code style and plans & specs location.

untra/operator · 3,628 tokens

dotfiles CLAUDE.md

Claude Code instructions for ooloth/dotfiles, covering claude.md, uphold project invariants, folder structure, symlink management and claude development workflow.

ooloth/dotfiles · 825 tokens

gemini-cli-desktop AGENTS.md

Instructions for Piebald-AI/gemini-cli-desktop, a project described as: Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.

Piebald-AI/gemini-cli-desktop · 6 tokens

sessionview AGENTS.md

Instructions for tyql688/sessionview, covering sessionview, commands, app / frontend, gates must pass under both feature sets: default (gui) and and --no-default-features --features headless.

tyql688/sessionview · 2,099 tokens

codmate AGENTS.md

Instructions for loocor/codmate, a project described as: CodMate is a macOS SwiftUI app for managing CLI AI sessions: browse, search, organize, resume, and review work produced by Codex, Claude Code, and Gemini CLI. It focuses on speed, a compact three-column UI, and “ship it” workflows like Project Review (Git…

loocor/codmate · 5,081 tokens

cordon AGENTS.md

AGENTS.md instructions for ilyautov/cordon, covering working in this repository, the three invariants, the map, commands and tests.

ilyautov/cordon · 1,405 tokens