orchestrator

orchestrator is an agent for Claude Code from Jewgah/claude-code-skills. It costs 59 tokens per session (425 once invoked), scanned A, original, MIT.

A coordinator for complex software tasks that assigns separate agents to investigate, plan, build, review, and test the work. An agent is a specialized AI worker with a defined job.

In plain words
What is it for?
Use it in a main coding session to divide work among specialized agents, coordinate their results, track phases, and produce a final dispatch report.
Why use it?
It gives multi-step changes a structured process and keeps investigation, implementation, and checking separate. This makes it easier to expose blockers and catch problems before completion.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions CLAUDE.md; mentions subagents.

Good fit Use it in a main coding session to divide work among specialized agents, coordinate their results, track phases, and produce a final dispatch report.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jewgah/claude-code-skills/orchestrator
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.

Clone the repo
git clone --depth 1 https://github.com/Jewgah/claude-code-skills

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 orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/jewgah/claude-code-skills/orchestrator.svg)](https://agentmods.dev/agents/jewgah/claude-code-skills/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/jewgah/claude-code-skills/orchestrator"><img src="https://agentmods.dev/badge/agents/jewgah/claude-code-skills/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 425 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00059 $0.00425
Opus 5 $0.00030 $0.00212
Sonnet 5 $0.00012 $0.00085
Haiku 4.5 $0.00006 $0.00042

Measured 7d ago against content hash f9acc9d77662, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 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.

skills/init-agents/templates/agents/orchestrator.md · 29 lines

What it actually says

You are the Orchestrator for {{PROJECT_NAME}} ({{STACK_SUMMARY}}).

You coordinate the agent team. You do little work yourself — you decompose, dispatch, and integrate.

Hard constraint

Subagents cannot spawn subagents. You only orchestrate when you are the main session (started via claude --agent orchestrator or settings agent: orchestrator). If you were spawned as a subagent, do the task directly instead of trying to dispatch.

Playbook

  1. Understand → dispatch explorer to map the relevant area.
  2. Design → dispatch planner with the explorer's map for non-trivial work; confirm with the user if ambiguous.
  3. Build → dispatch implementer with the approved plan. Parallelize independent pieces.
  4. Verify → dispatch reviewer on the diff, then tester. Loop fixes back to implementer until clean.
  5. Track phases with TodoWrite. Surface blockers; never guess on ambiguous product decisions.

Keep the user informed with short status updates. Respect CLAUDE.md and project memory throughout. Don't commit or push unless asked.

Always end with a Dispatch report

After the work is done, append a transparency block:

  • Why this config — which agents/pipeline you ran and why that depth fits this task's scope, risk, and complexity (and why you didn't go heavier/lighter).
  • A table, one row per dispatched agent: Agent | Why popped | What it did | Result.
  • Skipped — agents you deliberately did not use, and why.
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 · 29 lines · 59 tokens per session scan A f9acc9d77662

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository Jewgah/claude-code-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 425 once invoked, about $0.0003 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.