skill-multiagent-orchestration

skill-multiagent-orchestration is a skill for Claude Code, Codex from IAPro-Community/Orquestrador-Maestro. It costs 45 tokens per session (1,239 once invoked), scanned A, original, Apache-2.0.

A workflow for coordinating multiple coding agents on one engineering task. It divides independent work between agents while keeping the combined result safe to integrate.

In plain words
What is it for?
Use it to delegate implementation, research, testing, or review tasks to subagents, run independent work in parallel, and combine the results into one codebase.
Why use it?
It helps when one agent would take too long or when a task contains separate pieces that can be handled at the same time. It also reduces conflicts and unnecessary use of the agents’ context.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to delegate implementation, research, testing, or review tasks to subagents, run independent work in parallel, and combine the results into one codebase.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/iapro-community/orquestrador-maestro/skill-multiagent-orchestration
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.

Any agent
npx skills add IAPro-Community/Orquestrador-Maestro --skill skill-multiagent-orchestration
Clone the repo
git clone --depth 1 https://github.com/IAPro-Community/Orquestrador-Maestro

Made for: Claude Code, Codex.

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 skill-multiagent-orchestration

README.md
[![agentmods](https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/skill-multiagent-orchestration/github.svg)](https://agentmods.dev/skills/iapro-community/orquestrador-maestro/skill-multiagent-orchestration)
Your own site
<a href="https://agentmods.dev/skills/iapro-community/orquestrador-maestro/skill-multiagent-orchestration"><img src="https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/skill-multiagent-orchestration/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skill-multiagent-orchestration

Your own site · 80×15
<a href="https://agentmods.dev/skills/iapro-community/orquestrador-maestro/skill-multiagent-orchestration"><img src="https://agentmods.dev/badge/skills/iapro-community/orquestrador-maestro/skill-multiagent-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,239 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00045 $0.01239
Opus 5 $0.00023 $0.00620
Sonnet 5 $0.00009 $0.00248
Haiku 4.5 $0.00005 $0.00124

Measured 3d ago against content hash 5777a3af46be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

skill-multiagent-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.

codex/skills/skill-multiagent-orchestration/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multiagent Orchestration

Use this skill to decide whether multiagent execution is worth it, then divide work without creating merge conflicts, duplicated exploration, or excessive token use.

Start Here

Use multiagents only when at least one condition is true:

  • There are 2+ independent workstreams with different files, domains, or verification gates.
  • A broad audit can run in parallel with a local implementation.
  • The user explicitly asks for subagents, multiagents, team, swarm, or parallel execution.
  • A task is large enough that one agent would spend most of its time waiting on search, tests, or independent reviews.

Keep work solo when:

  • The next step is a blocking decision or a single-file change.
  • Agents would edit the same files.
  • The task requires one continuous mental model more than parallel throughput.
  • The overhead of prompts, review, and merge is larger than the work.

Execution Profiles

Fast

  • Agents: 0
  • Use for direct fixes, simple questions, small edits, and one obvious skill.
  • Goal: minimum context and fastest path.

Standard

  • Agents: 0-1
  • Use one sidecar agent only for independent research, review, or verification.
  • Main agent keeps the implementation path.

Deep

  • Agents: 2-4
  • Use for multi-system changes, project audits, SaaS builds, security hardening, or explicit parallel work.
  • Every agent needs a disjoint scope and a concrete output.

Team

  • Agents: 3-6
  • Use only when the work has clearly separable lanes such as frontend, backend, database, security, docs, and verification.
  • Require an integration owner.

Delegation Rules

Before spawning agents, write a short split:

  1. What stays with the lead agent.
  2. Which workstreams are independent.
  3. Which files or modules each agent owns.
  4. What each agent must return.
  5. Which validation command proves the integrated result.

Each delegated task must include:

  • Scope: exact files, directories, subsystem, or question.
  • Non-overlap: what the agent must not edit.
  • Output: patch summary, findings, changed paths, tests run, and blockers.
  • Constraint: do not revert or overwrite other agents' changes.
  • Verification: the smallest useful command or evidence for that lane.

Read the full file on GitHub · 145 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 Changed · +1 lines 5777a3af46be
  2. 12d ago First seen · 144 lines · 45 tokens per session scan A 101bc1b6fc7e

Subscribe to this mod's changes

skill-multiagent-orchestration is a skill published in the GitHub repository IAPro-Community/Orquestrador-Maestro (42 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 1,239 once invoked, about $0.0002 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.