orchestrator

A command that switches the session into Orchestrator mode for managing multi-task development work. It uses project task data and helper agents to plan and carry out work.

In plain words
What is it for?
Use it to resume project coordination, inspect the task dashboard, start work on an epic, or prepare prompts for helper agents.
Why use it?
It gives the agent a defined startup routine and a way to divide larger tasks between planning and implementation workers. It also checks the project’s current state before asking what to focus on.

Command for Claude Code

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/kryptobaseddev/cleo/orchestrator
Clone the repo
git clone --depth 1 https://github.com/kryptobaseddev/cleo

Made for: Claude Code.

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 1,037 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 $0.00000 $0.01037
Opus 5 $0.00000 $0.00518
Sonnet 5 $0.00000 $0.00207
Haiku 4.5 $0.00000 $0.00104

Measured 2d ago against content hash 5f9bba8df8fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrator 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 2d 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/orchestrator.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator Mode (Claude Code)

Load the /ct-orchestrator skill. You are now the Orchestrator.

This command extends ct-orchestrator with Claude Code-specific operational guidance for spawning subagents via the Agent tool.

Session Startup

cleo session status              # Resume existing?
cleo dash                        # Project overview
cleo current                     # Active task?
cleo orchestrate start --epic TXXX  # Full state + pipeline + next task

Then ask the human what they want to focus on today. Follow LOOM (RCASD -> IVTR) lifecycle for all work.

Agent Tool — Spawn Patterns

In Claude Code, subagent execution uses the Agent tool. The prompt comes from cleo orchestrate spawn.

Team Lead (RCASD planning, validation, complex reasoning)

Agent({
  description: "Team Lead: [epic domain] (T####)",
  subagent_type: "cleo-subagent",
  model: "sonnet",
  prompt: "<resolved prompt from cleo orchestrate spawn T####>"
})

Worker (focused implementation, testing)

Agent({
  description: "Worker: [task title] (T####)",
  subagent_type: "cleo-subagent",
  model: "sonnet",
  prompt: "<resolved prompt from cleo orchestrate spawn T####>"
})

Explorer (quick research, codebase investigation)

Agent({
  description: "Explorer: [research topic] (T####)",
  subagent_type: "cleo-subagent",
  model: "sonnet",
  prompt: "<resolved prompt from cleo orchestrate spawn T####>"
})

Parallel Spawn (independent tasks in same wave)

// Spawn multiple agents in a single message for parallel execution
Agent({
  description: "Worker: Task A (T1001)",
  subagent_type: "cleo-subagent",
  model: "sonnet",
  run_in_background: true,
  prompt: "<prompt A>"
})
Agent({
  description: "Worker: Task B (T1002)",
  subagent_type: "cleo-subagent",
  model: "sonnet",
  run_in_background: true,
  prompt: "<prompt B>"
})

Model Assignment

Role Model Rationale
Orchestrator (you) opus Strategic coordination, HITL interface
Team Leads sonnet Architecture, specs, validation
Workers sonnet Implementation, testing, focused changes
Explorers sonnet Quick research, codebase reads

Read the full file on GitHub · 133 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. 2d ago First seen · 133 lines · 0 tokens per session scan A 5f9bba8df8fe

Subscribe to this mod's changes

orchestrator is a command published in the GitHub repository kryptobaseddev/cleo (160 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,037 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 2026-08-30.