multi-agent-collaboration

multi-agent-collaboration is a skill for Claude Code, Codex from hajekim/agentic-design-patterns-skills. It costs 438 tokens per session (3,651 once invoked), scanned A, original, MIT.

A pattern for organizing several specialized agents into a coordinated team, with each agent handling a defined part of a larger task.

In plain words
What is it for?
Use it for multi-stage tasks, specialist teams, supervisor workflows, critic-reviewer loops, and work that can be divided into independent sub-problems.
Why use it?
Splitting work by specialty can make complex workflows easier to manage and allows one agent to review or improve another agent’s work.

Skill for Claude CodeCodex

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

Good fit Use it for multi-stage tasks, specialist teams, supervisor workflows, critic-reviewer loops, and work that can be divided into independent sub-problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hajekim/agentic-design-patterns-skills/multi-agent-collaboration
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 hajekim/agentic-design-patterns-skills --skill multi-agent-collaboration
Clone the repo
git clone --depth 1 https://github.com/hajekim/agentic-design-patterns-skills

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 multi-agent-collaboration

README.md
[![agentmods](https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/multi-agent-collaboration/github.svg)](https://agentmods.dev/skills/hajekim/agentic-design-patterns-skills/multi-agent-collaboration)
Your own site
<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-skills/multi-agent-collaboration"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/multi-agent-collaboration/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 multi-agent-collaboration

Your own site · 80×15
<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-skills/multi-agent-collaboration"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/multi-agent-collaboration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 438 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,651 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 $0.00438 $0.03651
Opus 5 $0.00219 $0.01826
Sonnet 5 $0.00088 $0.00730
Haiku 4.5 $0.00044 $0.00365

Measured 9d ago against content hash 96b03dd035dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

multi-agent-collaboration 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 9d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/multi-agent-collaboration/SKILL.md · 382 lines

How it starts

The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Agent Collaboration Pattern

Overview

The Multi-Agent Collaboration Pattern structures a system as a cooperative ensemble of distinct, specialized agents rather than a single monolithic agent. Each agent has a defined role, specific goals, and potentially unique tool access or domain knowledge. The power of this pattern lies in the interaction and synergy between agents — the collective output surpasses what any individual agent could produce alone.

Core Principle: Divide by specialization, conquer through cooperation — assign each agent what it does best, then orchestrate their collaboration.

When This Skill Applies

Activate this pattern when:

  • The task spans multiple domains requiring different types of expertise
  • Different phases of a workflow have fundamentally different requirements
  • A single agent would be overloaded by the breadth of tools and responsibilities
  • Quality improves through critic-reviewer feedback loops between agents
  • Scalability demands distributing work across independent specialized units
  • Tasks can be decomposed into sub-problems, each handled by a dedicated agent

Rule of thumb: Use Multi-Agent Collaboration when a task is complex enough that a human team of specialists would handle it better than a single generalist.

DEFINE → PLAN → ACTION Workflow

DEFINE

Map the collaboration requirements:

  1. What are the distinct sub-domains or phases of the task?
  2. What specialized role is needed for each sub-domain?
  3. How will agents communicate and hand off work?
  4. What is the overall orchestration model (sequential, parallel, hierarchical)?

PLAN

Design the multi-agent architecture:

  1. Define each agent with a clear role, goal, and tool set
  2. Choose the communication structure (Sequential, Network, Supervisor, Hierarchical, Custom)
  3. Design the handoff protocol: how does one agent's output become the next agent's input?
  4. Plan for agent failure: what happens if one specialist agent fails?
  5. Define the aggregation/synthesis step that produces the final unified output

Read the full file on GitHub · 382 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. 9d ago First seen · 382 lines · 438 tokens per session scan A 96b03dd035dd

Subscribe to this mod's changes

multi-agent-collaboration is a skill published in the GitHub repository hajekim/agentic-design-patterns-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 438 tokens to every session and 3,651 once invoked, about $0.0022 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

impact-audit

Blast radius of a change you have not made yet -- traces a symbol across federated repositories, splits impact per repo, and reports what must ship together.

n24q02m/better-code-review-graph · 35 tokens

onboard-repo

Index an unfamiliar codebase into the knowledge graph, then produce a first orientation map -- entry points, most-depended-upon modules, hotspots, test topology.

n24q02m/better-code-review-graph · 38 tokens

prompt-optimizer

Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite…

Jamkris/everything-gemini-code · 179 tokens

openclaw-persona-forge

A persona-design guide for OpenClaw agents, including their identity, personality, boundaries, names, and avatar prompts. OpenClaw is the specific agent platform this guide targets.

Jamkris/everything-gemini-code · 221 tokens

gemini-api

Google Gemini API patterns for Python and TypeScript. Covers content generation, streaming, tool use (function calling), vision, system instructions, context caching, batch requests, and agent workflows. Use when building applications with the Gemini API or Google Generative AI SDKs.

Jamkris/everything-gemini-code · 57 tokens

jira-integration

Use this skill when retrieving Jira tickets, analyzing requirements, updating ticket status, adding comments, or transitioning issues. Provides Jira API patterns via MCP or direct REST calls.

Jamkris/everything-gemini-code · 37 tokens