Skip to main content
skill CX Codex

sub-agent-orchestrator — Claude Code skill: how to install

sub-agent-orchestrator chains different agents so each step feeds the next, with the flow defined in YAML. Handles retries, timeouts and parallel branches.

MIT 267 installs ★ 440 updated 2026-10-20

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add OneWave-AI/claude-skills --skill sub-agent-orchestrator -a claude-code
Open on GitHub

What sub-agent-orchestrator does

The skill runs pipelines in which every step belongs to a separate agent that takes the previous agent's output. You describe roles, dependencies and handoffs in a YAML file. Supported shapes: sequential chains, parallel fan-out, routing by condition, loops gated by a validator, and map-reduce.

Before anything runs, it parses the file, checks required fields, agent references and circular dependencies, then asks you for missing inputs. Each agent's output is validated afterwards. When a step fails, retry and timeout rules apply, and the failure policy decides whether to skip it, abort, or switch to a fallback.

There are four modes: run an existing YAML file, describe a process in plain words (the skill writes the YAML and waits for your approval), dry run, and inspect with a text diagram. A dry run prints the plan without starting any agent, so do that before the first real run. The skill needs the Read, Write, Agent and Bash tools. Agent Army and Agent Swarm fan out identical work in parallel; this one links different steps where A's output becomes B's input.

What it helps with

  • chain agents so one agent's output becomes the next one's input
  • send one input to several agents and merge their scores into one result
  • route incoming data to the right agent based on a classification
  • repeat a step in a loop until a validator accepts the result
  • split a large input into chunks, process them and recombine the answers

Example prompts for the agent

  • Use sub-agent-orchestrator to run the agent chain from my YAML file
  • Draft a YAML pipeline from this description with sub-agent-orchestrator and show it for approval
  • Do a dry run with sub-agent-orchestrator: print the plan, start no agents

How to install sub-agent-orchestrator

1Skills CLI (Vercel)

npx skills add OneWave-AI/claude-skills --skill sub-agent-orchestrator -a claude-code

2Manually: put the files in place

~/.claude/skills/sub-agent-orchestrator/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/sub-agent-orchestrator/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about sub-agent-orchestrator

How do I install sub-agent-orchestrator in Claude Code?

Run npx skills add OneWave-AI/claude-skills --skill sub-agent-orchestrator -a claude-code. The skill lands in ~/.claude/skills/sub-agent-orchestrator/SKILL.md.

What does sub-agent-orchestrator do?

It runs chains of different agents where one agent's result feeds the next. The flow lives in YAML, and the skill handles step order, retries, timeouts and output checks.

How is sub-agent-orchestrator different from Agent Army and Agent Swarm?

Those two run the same kind of work in parallel: code changes and data processing. This skill connects dissimilar steps, where A's output is B's input.

Source text

SKILL.md · MIT
---
name: sub-agent-orchestrator
description: Manages parent/child agent relationships with task delegation and result aggregation. Supports sequential chains, parallel fans, conditional routing, retry logic, timeout handling, and YAML-based visual workflow definition.
tools: Read, Write, Agent, Bash
user_invocable: true
---

# Sub-Agent Orchestrator

Design and execute multi-agent pipelines where each step is a different agent that depends on the previous one. Define roles, dependencies, and handoffs in YAML, then run sequential, parallel, conditional, loop, and map-reduce workflows with retry, timeout, and validation.

Unlike Agent Army (homogeneous parallel code changes) and Agent Swarm (homogeneous parallel data processing), this orchestrator coordinates heterogeneous pipelines where the output of A feeds the input of B.

## Contents

- `references/patterns.md` -- The six workflow patterns and the comparison to Agent Army/Swarm.
- `references/workflow-schema.md` -- Full YAML workflow definition language.
- `references/examples.md` -- Complete worked workflows (research-to-proposal, lead scoring).
- `references/execution-engine.md` -- Per-step execution model, retry, timeout, validation, edge cases.
- `references/templates.md` -- Reusable workflow scaffolds.
- `references/visual-and-reporting.md` -- Text diagrams and the execution report template.

## Workflow

1. Determine the mode from the request:
   - Run a workflow file: read the YAML at the given path.
   - Define and run inline: convert the natural-language description into a workflow YAML (see `references/workflow-schema.md`), then show it for approval.
   - Dry run: parse, validate, resolve inputs, and show the execution plan without deploying agents.
   - Inspect: parse the YAML and produce a human-readable description plus a text diagram (see `references/visual-and-reporting.md`).

2. Parse and validate the workflow: confirm required fields, that agent IDs resolve, and that there are no circular dependencies. Report syntax or reference errors with the offending line. See `references/execution-engine.md`.

3. Resolve inputs: collect every required input from the user before starting; apply defaults for optional inputs.

4. Build the execution DAG and run each step in topological order using the matching execution model (sequential, parallel, conditional, loop, map). See `references/execution-engine.md`.

5. After each agent completes, validate its output against the agent's schema and rules. On failure, apply the retry/timeout/failure policy (skip, abort, or fallback).

6. On completion, present results using the execution report template in `references/visual-and-reporting.md`. For partial or failed runs, report what completed, what failed, and any collected partial output.

## Choosing a pattern

Match the task shape to a pattern, then scaffold from `references/templates.md`:

- Strict ordering of distinct steps: sequential chain.
- One input scored or analyzed from multiple angles: parallel fan-out/fan-in.
- Input routed by classification: conditional routing.
- Output must meet a quality bar: loop with a validator.
- Large input chunked and recombined: map-reduce.
- A step needs a backup approach on failure: pipeline with fallback.

See `references/patterns.md` for diagrams and examples of each.

© OneWave-AI · MIT · OneWave-AI/claude-skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set185

The whole set →
brand-voice-analyzer brand-voice-analyzer extracts tone, vocabulary, and structure from company copy to build a style guide and audit drafts against it. CX Codex +1 281installs weekly-business-report weekly-business-report is a Claude Code skill that collects weekly KPIs from enabled sources, compares them with targets and prior weeks, and saves a report. It brings business figures into a shared weekly view. CX Codex +1 276installs client-health-dashboard client-health-dashboard builds a client health view from CRM and engagement data, then produces a risk-ranked report with scores, trends, and next actions. CX Codex +1 276installs hiring-scorecard Builds a structured hiring scorecard for any role with weighted competencies, interview questions, evaluation matrix, red/green flags, and reference check questions. CX Codex +1 268installs database-migrator database-migrator moves schemas, data, and database logic across PostgreSQL, MySQL, Supabase, PlanetScale, and MongoDB. Useful when a migration needs checks and a rollback plan. CX Codex +1 267installs agent-to-agent agent-to-agent coordinates multi-agent workflows across Claude agents using shared context files, structured handoffs, and predefined orchestration patterns. CX Codex +1 263installs pricing-strategy Builds a pricing strategy for a product or service: analyzes costs, researches competitors, selects a model (cost-plus, value-based, penetration, premium), designs tier structure, projects revenue. CX Codex +1 260installs ai-readiness-assessment ai-readiness-assessment evaluates business readiness for AI adoption across six dimensions and generates an ai-readiness-report.md document with gap analysis. CX Codex +1 260installs

Project sponsors

Companies that keep this analytics open