multi-agent-orchestration

multi-agent-orchestration is a skill for Claude Code, Codex from Hoja-Solutions/agent-stdlib. It costs 160 tokens per session (831 once invoked), scanned A, original, MIT.

A research workflow in which a lead agent divides a broad question among three to five worker agents, then combines their findings. Each worker has its own context, or working memory, while the lead coordinates the overall investigation.

In plain words
What is it for?
Use it for literature surveys, evidence gathering, and mapping a large unfamiliar topic. It helps decide whether parallel workers are worthwhile, assign non-overlapping tasks, and synthesize their results.
Why use it?
It covers more independent sources or subquestions than one agent can comfortably handle at once. It also explains when this approach is unsuitable, such as tightly connected coding work where agents may conflict.

Skill for Claude CodeCodex

Part of the agent-stdlib plugin — 14 skills, 2 commands, 1 agent, 2 hooks, 2 MCP servers 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/hoja-solutions/agent-stdlib/multi-agent-orchestration
Any agent
npx skills add Hoja-Solutions/agent-stdlib --skill multi-agent-orchestration
Clone the repo
git clone --depth 1 https://github.com/Hoja-Solutions/agent-stdlib

Made for: Claude Code, Codex.

Or install agent-stdlib, the plugin that ships this one along with the rest of its 14 skills, 2 commands, 1 agent, 2 hooks, 2 MCP servers.

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 multi-agent-orchestration

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoja-solutions/agent-stdlib/multi-agent-orchestration.svg)](https://agentmods.dev/skills/hoja-solutions/agent-stdlib/multi-agent-orchestration)
Your own site
<a href="https://agentmods.dev/skills/hoja-solutions/agent-stdlib/multi-agent-orchestration"><img src="https://agentmods.dev/badge/skills/hoja-solutions/agent-stdlib/multi-agent-orchestration.svg" alt="Measured on agentmods" height="20"></a>
Per session 160 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 831 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 $0.00160 $0.00831
Opus 5 $0.00080 $0.00415
Sonnet 5 $0.00032 $0.00166
Haiku 4.5 $0.00016 $0.00083

Measured 3d ago against content hash a8a84fedd0b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

multi-agent-orchestration 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 3d 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/multi-agent-orchestration/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-agent orchestration

Source: How we built our multi-agent research system. The pattern lives in Anthropic's cookbook as notebooks and prompts. This packages the parallel-research recipe as a skill, with the judgment of when to use it. The pack also ships a /research command and a research-worker subagent that run this flow.

A lead agent plans a question, spawns several subagents to chase parts of it in parallel, and synthesizes what they return. Each subagent has its own context window, so the system explores far more ground than one agent could hold at once. That power has a price, so the first decision is whether to use it at all.

Use it for breadth, not for coupling

Multi-agent fits work that splits into independent pieces explored at the same time: surveying a literature, gathering evidence from many sources, mapping a large unknown space. It fits poorly when the pieces depend on each other.

Do not reach for it on a coding task with shared state, or anything that needs tight coordination between the parts, because the subagents cannot see each other's context and will step on the shared thing. A multi-agent run also costs on the order of 15 times the tokens of a single chat. Spend that only when the breadth is worth it.

Delegate so workers do not collide

A vague subagent prompt produces overlap and gaps. Give each worker four things:

  • a specific objective, narrow enough that two workers will not duplicate it
  • the output format you want back
  • guidance on which tools to use
  • explicit boundaries on what to leave to other workers

Scale the effort to the task. A simple question wants one agent and a handful of tool calls. A complex one warrants ten or more subagents. Stating the scale in the lead's plan stops it from over- or under-spawning.

Search broad, then narrow

Have agents open with broad queries to map the space, then tighten toward the specifics. Use extended or interleaved thinking in the lead for planning the decomposition and for judging what comes back, so the synthesis reacts to the findings rather than to the original plan.

Read the full file on GitHub · 56 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. 3d ago First seen · 56 lines · 160 tokens per session scan A a8a84fedd0b1

Subscribe to this mod's changes

multi-agent-orchestration is a skill published in the GitHub repository Hoja-Solutions/agent-stdlib (1 stars, last pushed 1mo ago), licensed MIT. It adds 160 tokens to every session and 831 once invoked, about $0.0008 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.