multi-agent-orchestration

multi-agent-orchestration is a skill for Claude Code, Codex from int2t05/engineering-skills. It costs 103 tokens per session (1,312 once invoked), scanned A, original, MIT.

A workflow for carrying out coding tasks with multiple subagents, meaning separate agent sessions with focused context. It supports parallel work and planned sequences with review checkpoints.

In plain words
What is it for?
Dispatching independent tasks in parallel or running a larger plan through implementer subagents one step at a time.
Why use it?
It helps handle work that is too large for one session or can be safely divided into independent tasks. Reviews between stages help catch problems before later work begins.

Skill for Claude CodeCodex

Written for Claude Code and Codex: ${CLAUDE_PLUGIN_ROOT} variable, but also agents/openai.yaml present. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the engineering-skills plugin — 47 skills, 1 hook shipped together

Good fit Dispatching independent tasks in parallel or running a larger plan through implementer subagents one step at a time.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add int2t05/engineering-skills
Claude Code
/plugin install engineering-skills

Made for: Claude Code, Codex.

Or install engineering-skills, the plugin that ships this one along with the rest of its 47 skills, 1 hook.

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/int2t05/engineering-skills/multi-agent-orchestration.svg)](https://agentmods.dev/skills/int2t05/engineering-skills/multi-agent-orchestration)
Your own site
<a href="https://agentmods.dev/skills/int2t05/engineering-skills/multi-agent-orchestration"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/multi-agent-orchestration.svg" alt="Measured on agentmods" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,312 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00103 $0.01312
Opus 5 $0.00051 $0.00656
Sonnet 5 $0.00021 $0.00262
Haiku 4.5 $0.00010 $0.00131

Measured 7d ago against content hash e1bc1366aea7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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/04-develop/multi-agent-orchestration/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Agent Orchestration

Execute work through subagents instead of a single context. Two modes: parallel dispatch (independent tasks to concurrent isolated-context agents) and plan-driven execution (a plan as a sequence of implementer-subagents, each reviewed before the next). Use when the work exceeds one context window, or when isolation prevents cross-task contamination.

When to use

  • A plan/ticket set is too large for one session — drive it as sequenced implementer-subagents
  • 2+ independent tasks that don't share state — dispatch them concurrently to isolated contexts
  • A task needs a fresh context to avoid prior-session bias or context bloat
  • Reviewing one task's output before starting the next (plan-driven checkpoint)
  • Triggers on "parallel agents", "subagent execution", "dispatch tasks", "fan out", "并行 agent", "子代理执行", "派发任务"

Not for: breaking a plan into tickets (use breakdown — this skill executes the tickets, it doesn't decompose them); doing the implementation yourself in one context (use implement); single-task work that fits one session (just do it — orchestration has overhead).

Steps

1. Decide: parallel dispatch or plan-driven execution?

  • Parallel dispatch — the tasks are independent (no data dependency between them). Run them concurrently. Use when: lint-fixing N files, researching N competitors, generating N independent components.
  • Plan-driven execution — the tasks have an order (each informs or gates the next). Run them sequentially with review between. Use when: a feature spans schema → API → UI → tests, or when task N's output must be verified before task N+1 starts.

If tasks are independent but few (2-3) and each is small, don't orchestrate — do them inline. Orchestration earns its overhead only when isolation or scale matters.

2. Construct the context for each subagent

A subagent has no access to your conversation — its context is only what you put in its prompt. Construct it deliberately:

Read the full file on GitHub · 79 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 79 lines · 103 tokens per session scan A e1bc1366aea7

Subscribe to this mod's changes

multi-agent-orchestration is a skill published in the GitHub repository int2t05/engineering-skills (3 stars, last pushed 6d ago), licensed MIT. It adds 103 tokens to every session and 1,312 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

memory-to-skill

Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…

zilliztech/memsearch · 82 tokens

pr-workflow

Crear pull requests completas con descripcion, labels y reviewers.

686f6c61/alfred-dev · 14 tokens

memory

This skill should be used when the user asks to record a design decision, search past project decisions, inspect the Alfred memory timeline, or work with the alfred-memory MCP server. Use it to call the namespaced MCP tools instead of inventing history.

686f6c61/alfred-dev · 53 tokens

performance-audit

Full-stack performance health check across 12 dimensions. Rendering, bundles, assets, API/network, algorithms, memory, database, caching, Web Vitals, backend runtime, concurrency, and framework-specific pathologies. Evidence-based Impact Models with confidence tiers and a prioritized optimization roadmap. Switches…

greglas75/zuvo · 90 tokens

init

Opt-in onboarding for the mARC agent team. Scaffolds a per-repo team binding so the team graduates from ephemeral session-memory to persistent, versioned config — without ever writing a file silently. Discovers the repo's org/repo/ project at runtime via gh, prefills {{ agentsdir }}/team.toml, and (optionally) a lean…

NexaDuo/mARC · 122 tokens

fec-image-generation

A workflow for creating or editing images and diagrams, from posters and product mockups to academic graphics, illustrations, and system maps. For text-heavy technical diagrams, it can use editable sources such as Mermaid, SVG, HTML, or canvas before exporting an image.

bovinphang/frontend-craft · 256 tokens