cc-orchestrate

cc-orchestrate is a command for Claude Code from TheLobbi/claude. It costs 0 tokens per session (3,961 once invoked), scanned A, original, MIT.

A command that deploys ready-made groups of coding agents for different development tasks. It can use subagents that report to one coordinator or agent teams whose members communicate with one another.

In plain words
What is it for?
Use it to run coordinated development, research, code review, or testing work. Choose simpler subagents for independent tasks or communicating agent teams for work that needs collaboration.
Why use it?
It removes the need to design and start a multi-agent setup by hand. You can preview templates, check running work, and optionally prepare separate Git worktrees for parallel changes.

Command for Claude Code

Part of the claude-orchestration plugin — 6 skills, 133 commands, 9 agents, 8 hooks, 6 plugins shipped together

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 commands/thelobbi/claude/cc-orchestrate
Clone the repo
git clone --depth 1 https://github.com/TheLobbi/claude

Made for: Claude Code.

Or install claude-orchestration, the plugin that ships this one along with the rest of its 6 skills, 133 commands, 9 agents, 8 hooks, 6 plugins.

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 cc-orchestrate

README.md
[![agentmods](https://agentmods.dev/badge/commands/thelobbi/claude/cc-orchestrate.svg)](https://agentmods.dev/commands/thelobbi/claude/cc-orchestrate)
Your own site
<a href="https://agentmods.dev/commands/thelobbi/claude/cc-orchestrate"><img src="https://agentmods.dev/badge/commands/thelobbi/claude/cc-orchestrate.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,961 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00000 $0.03961
Opus 5 $0.00000 $0.01980
Sonnet 5 $0.00000 $0.00792
Haiku 4.5 $0.00000 $0.00396

Measured 5d ago against content hash 7eff22733934, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

cc-orchestrate 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 5d 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/commands/cc-orchestrate.md · 610 lines

How it starts

The opening of the file, as written. The whole thing — 610 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/cc-orchestrate — Agent Team Templates & Multi-Agent Orchestration

Deploy pre-built agent team configurations for common development patterns. Choose between subagent patterns (hub-and-spoke) and full Agent Teams (mesh coordination) based on your task complexity.

Usage

/cc-orchestrate                          # Interactive template picker
/cc-orchestrate --template builder-validator   # Deploy specific template
/cc-orchestrate --template qa-swarm            # QA testing swarm
/cc-orchestrate --list                         # List all available templates
/cc-orchestrate --status                       # Check running teams/subagents
/cc-orchestrate --dry-run                      # Show template without deploying
/cc-orchestrate --worktree                     # Set up git worktrees for parallel agents

When to Use Subagents vs Agent Teams

Decision Framework

Does the task need workers to communicate with each other?
├── NO → Use Subagents (hub-and-spoke)
│   • Workers report results to parent only
│   • Lower token cost (results summarized)
│   • No setup needed (built-in)
│   • Best for: research, review, focused deep-dives
│
└── YES → Use Agent Teams (mesh network)
    • Workers message each other directly
    • Shared task list with self-claiming
    • Higher cost (~3-5x, each is a full session)
    • Best for: multi-component features, debates, cross-layer work

Cost Comparison

Pattern Agents Tokens/Task Best For
Single agent 1 ~50k Simple changes
Subagents 1 lead + 2-4 workers ~100-200k Focused parallel work
Agent Team (small) 3-5 teammates ~250-500k Multi-component features
Agent Team (swarm) 5-10 teammates ~500k-1M Large-scale review/QA

Template Library

Template 1: Builder-Validator (Subagent Pattern)

When: Any implementation task where quality matters. Pattern: Builder implements, Validator reviews and catches issues.

Read the full file on GitHub · 610 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. 5d ago First seen · 610 lines · 0 tokens per session scan A 7eff22733934

Subscribe to this mod's changes

cc-orchestrate is a command published in the GitHub repository TheLobbi/claude (21 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,961 tokens. 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.