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.
npx skills add TheophilusChinomona/claude-openclaw-plugin --skill openclaw-multi-agent-team-setupgit clone --depth 1 https://github.com/TheophilusChinomona/claude-openclaw-pluginWrote 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.
[](https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-multi-agent-team-setup)<a href="https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-multi-agent-team-setup"><img src="https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-multi-agent-team-setup/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.
<a href="https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-multi-agent-team-setup"><img src="https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-multi-agent-team-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00066 | $0.03074 |
| Opus 5 | $0.00033 | $0.01537 |
| Sonnet 5 | $0.00013 | $0.00615 |
| Haiku 4.5 | $0.00007 | $0.00307 |
Grade A, and why
openclaw-multi-agent-team-setup 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building a Multi-Agent Team in OpenClaw
End-to-end guide for turning a single OpenClaw gateway into a collaborative multi-agent operating system. Based on real-world patterns from production multi-agent deployments.
Prerequisite skills: This guide builds on concepts from
openclaw-multi-agent(config syntax, bindings),openclaw-agent-teams(SOUL.md authoring, hierarchy design, memory architecture), andopenclaw-sessions(session mechanics). Reference those skills for deeper coverage of individual topics.
Overview: What Is an "Agent OS"?
An Agent OS is a single OpenClaw gateway running multiple agents with:
- Independent workspaces — each agent has its own personality, rules, memory, and sessions
- Deterministic routing — messages reach the right agent via explicit bindings, not guesswork
- Collaboration rules — agents work together through structured protocols, not free-form chat
- Dual-track governance — config-layer hard constraints + prompt-layer behavioral guidance
Example 5-role team:
| Role | Responsibility | Model Tier | Tool Access |
|---|---|---|---|
| Commander | Situational awareness, task decomposition, assignment, closing | High (claude-sonnet-4-6+) | Full |
| Strategist | Strategic analysis, risk prediction, scheme evaluation | High | Read-heavy |
| Engineer | Code implementation, system maintenance, technical execution | High | Full + exec |
| Creator | Content creation, expression optimization, external output | Mid | Write + web |
| Think Tank | Knowledge auditing, quality control, compliance checks | Mid | Read-only |
Start with 3 roles, validate the routing and collaboration patterns, then add incrementally. Going from 1 to 5 agents at once multiplies debugging surface.
Architecture
Single Gateway Process
├── Channel Connectors (Discord, Telegram, ...)
│ └── Bindings (channel + accountId → agentId)
├── Agent 1: Commander
│ ├── Workspace (SOUL.md, AGENTS.md, rules, memory)
│ ├── State directory (auth, config)
│ └── Session store (isolated per scope)
├── Agent 2: Strategist
│ └── ... (independent workspace, state, sessions)
├── Agent 3: Engineer
│ └── ...
├── Agent 4: Creator
│ └── ...
└── Agent 5: Think Tank
└── ...
What ships with it
1 file 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.
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.
- 11d ago First seen · 342 lines · 66 tokens per session scan A 259c91cb004e
openclaw-multi-agent-team-setup is a skill published in the GitHub repository TheophilusChinomona/claude-openclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 3,074 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…