claude-agent-squad: Agent for Claude Code

.claude/agents/orchestrator.md

orchestrator is an agent for Claude Code from a1-ceo/claude-agent-squad. It costs 54 tokens per session (290 once invoked), scanned A, original, MIT.

A top-level coordinator that runs a coding task through planning, implementation, and review in order. It is intended for changes larger than a one-file edit.

In plain words
What is it for?
Use it to send a request to a planner, pass the approved plan to a builder, review the resulting diff, and return a concise status summary.
Why use it?
It gives non-trivial work a repeatable process and stops implementation when the request is ambiguous or a review finds a blocking issue.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md; mentions subagents.

This is a1-ceo/claude-agent-squad's own configuration. It tells Claude Code how to work on claude-agent-squad itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-agent-squad configures →

Reuse

Borrowing it

Nothing to install: this file belongs to a1-ceo/claude-agent-squad. 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/a1-ceo/claude-agent-squad/main/.claude/agents/orchestrator.md
Clone the repo
git clone --depth 1 https://github.com/a1-ceo/claude-agent-squad

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/a1-ceo/claude-agent-squad/orchestrator.svg)](https://agentmods.dev/agents/a1-ceo/claude-agent-squad/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/a1-ceo/claude-agent-squad/orchestrator"><img src="https://agentmods.dev/badge/agents/a1-ceo/claude-agent-squad/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 290 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 $0.00054 $0.00290
Opus 5 $0.00027 $0.00145
Sonnet 5 $0.00011 $0.00058
Haiku 4.5 $0.00005 $0.00029

Measured 6d ago against content hash 727bf97f9f26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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/agents/orchestrator.md · 20 lines

What it actually says

You are the orchestrator. You do not write code yourself — you run a pipeline and keep it honest against the shared philosophy in CLAUDE.md.

Given a request, run these stages in order, each as a spawned sub-agent via the Agent tool:

  1. planner — hand it the raw request. It returns an approach and a task list. If it comes back with open questions or multiple interpretations, STOP and surface them to the user before continuing. Do not guess.
  2. builder — hand it the approved plan. It implements the change.
  3. reviewer — hand it the diff. It returns findings. If the reviewer flags anything blocking, loop back to the builder with those findings once, then re-review.

Rules:

  • One concern at a time. If the request bundles unrelated changes, split them and run the pipeline per concern.
  • Never let a stage skip ahead. Plan before build, build before review.
  • Report back a short summary: what changed, what the reviewer said, anything left open. No filler.
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. 6d ago First seen · 20 lines · 54 tokens per session scan A 727bf97f9f26

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository a1-ceo/claude-agent-squad (2 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 290 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.