orchestrator

orchestrator is a skill for Claude Code from richfrem/agent-plugins-skills. It costs 96 tokens per session (3,194 once invoked), scanned A, original, MIT.

A routing workflow that examines an incoming task and chooses the most suitable agent workflow. An orchestrator is a coordinator that directs work to specialized processes.

In plain words
What is it for?
Use it to route research, implementation, review, or self-improvement tasks and manage their completion steps.
Why use it?
It helps when a request is unclear or could fit several workflows, reducing the need to choose the process manually.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; mentions Codex.

Part of the agent-orchestration plugin — 9 skills, 1 agent 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 skills/richfrem/agent-plugins-skills/orchestrator
Any agent
npx skills add richfrem/agent-plugins-skills --skill orchestrator
Clone the repo
git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

Made for: Claude Code.

Or install agent-orchestration, the plugin that ships this one along with the rest of its 9 skills, 1 agent.

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/skills/richfrem/agent-plugins-skills/orchestrator.svg)](https://agentmods.dev/skills/richfrem/agent-plugins-skills/orchestrator)
Your own site
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/orchestrator"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,194 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00096 $0.03194
Opus 5 $0.00048 $0.01597
Sonnet 5 $0.00019 $0.00639
Haiku 4.5 $0.00010 $0.00319

Measured 2d ago against content hash 5a17b7ea87f2, 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 1 finding 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.

The scan reads SKILL.md. This mod also ships 3 executable files (references/agent_orchestrator.py, scripts/agent_orchestrator.py, scripts/swarm_run.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **CRITICAL**: When executing sub-agent commands in background or headless scripts (e.g., via `run_agent.py` or system subprocess runners), you must redirect standard input (e.g., `stdin=subprocess.DEVNULL` or `< /dev/n
plugins/agent-orchestration/skills/orchestrator/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dependencies

This skill requires Python 3.8+ and standard library only. No external packages needed.

To install this skill's dependencies:

pip-compile ./requirements.in
pip install -r ./requirements.txt

See ./requirements.txt for the dependency lockfile (currently empty — standard library only).


Orchestrator: Loop Router & Lifecycle Manager

The Orchestrator assesses the incoming trigger, selects the right loop pattern, and manages the shared closure sequence (seal, persist, retrospective, self-improvement).

The Core Loop

Ecosystem Context

Routing Decision Tree

Use this to select the correct execution pattern (for interactive navigation, invoke the select-loop-strategy skill):

1. Does the task require formal state machine transitions, human gates, worktree sandboxing, and rollback?
   └─ YES → Pattern 6: graph-execution

2. Does the trigger mention unguided friction evaluation, tests, and self-optimization?
   └─ YES → Pattern 5: triple-loop-learning

3. Does it need adversarial review before proceeding?
   └─ YES → Pattern 2: red-team-review

4. Can the work be split into parallel independent tasks?
   └─ YES → Pattern 4: agent-swarm

5. Does it require hierarchical delegation (Outer Director managing git vs. Inner Worker)?
   └─ YES → Pattern 3: dual-loop

6. Is this work I can do entirely myself (research, document, iterate in single context)?
   └─ YES → Pattern 1: learning-loop
Signal Pattern Skill
Research question, knowledge gap, documentation task Simple Learning learning-loop
Architecture decision, security review, high-risk change Red Team Review red-team-review
Feature implementation, bug fix, single work package Dual-Loop dual-loop
Large feature, bulk migration, multi-concern parallel work Agent Swarm agent-swarm
Systemic rules generation, autonomous meta-optimizations Triple-Loop triple-loop-learning
State-machine transitions, worktree sandboxing, receipt gates Graph Execution graph-execution
Selecting or comparing orchestration topologies Strategy Selector select-loop-strategy

Read the full file on GitHub · 243 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 Changed · +2 lines 5a17b7ea87f2
  2. 6d ago First seen · 241 lines · 96 tokens per session scan A ddde4cb73f24

Subscribe to this mod's changes

orchestrator is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 3,194 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.