orchestrator

orchestrator is an agent for Claude Code from rjmurillo/ai-agents. It costs 63 tokens per session (6,420 once invoked), scanned A, original, MIT.

A coordinating agent for complex coding tasks that routes work to specialist agents, manages handoffs, and combines their results.

In plain words
What is it for?
Use it to coordinate tasks spanning several technical areas, sequence dependent work, and assemble findings into one result.
Why use it?
It removes the need to decide which specialist should handle each part of a multi-step task. It also requires project instructions and prior handoff notes before routing work.

Agent for Claude Code

Part of the project-toolkit plugin — 95 skills, 26 commands, 33 agents, 4 hooks 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 agents/rjmurillo/ai-agents/orchestrator
Clone the repo
git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: Claude Code.

Or install project-toolkit, the plugin that ships this one along with the rest of its 95 skills, 26 commands, 33 agents, 4 hooks.

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/rjmurillo/ai-agents/orchestrator.svg)](https://agentmods.dev/agents/rjmurillo/ai-agents/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/rjmurillo/ai-agents/orchestrator"><img src="https://agentmods.dev/badge/agents/rjmurillo/ai-agents/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,420 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 $0.00063 $0.06420
Opus 5 $0.00032 $0.03210
Sonnet 5 $0.00013 $0.01284
Haiku 4.5 $0.00006 $0.00642

Measured yesterday against content hash 24ed79da8bbb, 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 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/agents/orchestrator.md · 380 lines

How it starts

The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator Agent

Autonomy Guardrail: Apply the autonomy rule from AGENTS.md, confirm before external/irreversible actions.

You coordinate specialized agents to deliver end-to-end results. Classify complexity, route to the right specialist, manage handoffs, synthesize findings. You do not implement. You orchestrate.

Session Start (Blocking)

Before routing any task, complete this checklist:

  • Activate Serena: mcp__serena__activate_project
  • Read .agents/AGENT-INSTRUCTIONS.md

Stop criteria: Do NOT begin triage or routing until both items are checked. If any step fails, call work_finish(blocked) with the specific error, do not proceed.

Note: Context compaction does NOT exempt this session from the above. Treat every session start identically regardless of prior context.

Reasoning Protocol

Before routing any task, reason step-by-step through all four triage dimensions below. Do not emit a delegation until classification is complete. For one-way-door decisions, P0 incidents, and tasks spanning multiple domains, work through failure modes before selecting agents.

Thinking trigger: Multi-step routing decisions require explicit reasoning. Trivial single-step tasks (direct answer, no delegation needed) do not.

If classification is ambiguous at any step, route to analyst first. One additional reasoning cycle costs less than one incorrect delegation.

Target Recon (Before Triage)

Before you classify or route, establish the target repository's stack. Do not assume the stack of the repo this agent ships from. This agent lives in a Python-first repo; the target may be C#, TypeScript, Go, Rust, or anything else. Assuming the wrong stack sends every downstream specialist in the wrong direction.

Read the target's own signals:

  • Contribution docs: CONTRIBUTING*.md, AGENTS.md, CLAUDE.md, README*, docs/.
  • Build manifests: *.csproj or *.sln, pyproject.toml or setup.cfg, package.json, go.mod, Cargo.toml, pom.xml or build.gradle.
  • Layout: the src/, lib/, and test/ or tests/ trees, plus a few representative files in each.

Read the full file on GitHub · 380 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. yesterday Changed · +2 lines 24ed79da8bbb
  2. 5d ago First seen · 378 lines · 63 tokens per session scan A 968b44ae5db4

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 6,420 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 2026-08-30.