openclaw-multi-agent

openclaw-multi-agent is a skill for Claude Code from TheophilusChinomona/claude-openclaw-plugin. It costs 53 tokens per session (1,145 once invoked), scanned A, original, MIT.

A setup guide for running multiple isolated agents in OpenClaw, an agent platform. It covers separate workspaces, stored sessions, message routing, and per-agent policies.

In plain words
What is it for?
Use it to add agents, create their workspaces, route direct or group messages, and configure separate permissions and tool rules.
Why use it?
It prevents agents from sharing the wrong files, login state, or conversation history and explains how incoming messages reach the right agent.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md; built for openclaw.

Part of the openclaw plugin — 31 skills, 22 commands, 4 agents, 3 hooks shipped together

Good fit Use it to add agents, create their workspaces, route direct or group messages, and configure separate permissions and tool rules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/theophiluschinomona/claude-openclaw-plugin/openclaw-multi-agent
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 TheophilusChinomona/claude-openclaw-plugin --skill openclaw-multi-agent
Clone the repo
git clone --depth 1 https://github.com/TheophilusChinomona/claude-openclaw-plugin

Made for: Claude Code.

Or install openclaw, the plugin that ships this one along with the rest of its 31 skills, 22 commands, 4 agents, 3 hooks.

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 openclaw-multi-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-multi-agent/github.svg)](https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-multi-agent)
Your own site
<a href="https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-multi-agent"><img src="https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-multi-agent/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 openclaw-multi-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-multi-agent"><img src="https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-multi-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,145 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 $0.00053 $0.01145
Opus 5 $0.00026 $0.00573
Sonnet 5 $0.00011 $0.00229
Haiku 4.5 $0.00005 $0.00114

Measured 12d ago against content hash f330c3280554, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

openclaw-multi-agent 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 12d 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.

plugins/openclaw/skills/openclaw-multi-agent/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenClaw Multi-Agent Setup

Guide the user through configuring multiple agents with routing, isolation, and per-agent policies.

Agent Concept

An agent in OpenClaw is an isolated brain with three components:

  • Workspace - Contains personality files (SOUL.md, AGENTS.md, USER.md), local notes, and persona rules. Default working directory for tool execution.
  • State directory (agentDir) - Stores auth profiles, model registry, and per-agent config at ~/.openclaw/agents/<agentId>/agent. Auth profiles are per-agent and never shared automatically.
  • Session store - Chat history at ~/.openclaw/agents/<agentId>/sessions.

Never reuse agentDir across agents - causes auth/session collisions.

Creating Agents

openclaw agents add work

This creates:

  • Workspace at ~/.openclaw/workspace-work
  • State at ~/.openclaw/agents/work/agent
  • Sessions at ~/.openclaw/agents/work/sessions

Verify: openclaw agents list --bindings

Binding Rules (Message Routing)

Messages route to agents via deterministic, most-specific-wins bindings:

  1. Peer match (exact DM/group ID) - highest priority
  2. Parent peer match (thread inheritance)
  3. Guild ID + roles (Discord)
  4. Guild ID (Discord)
  5. Team ID (Slack)
  6. Account ID match
  7. Channel-level (accountId: "*")
  8. Default agent fallback

If multiple bindings match the same tier, first in config order wins. Multiple fields in a binding use AND semantics.

{
  bindings: [
    // Most specific (peer) - wins over channel-wide
    { agentId: "opus", match: { channel: "whatsapp", peer: { kind: "direct", id: "+15551234567" } } },
    // Channel-wide fallback
    { agentId: "chat", match: { channel: "whatsapp" } },
  ],
}

Per-Agent Configuration

{
  agents: {
    list: [
      {
        id: "work",
        workspace: "~/.openclaw/workspace-work",
        model: { primary: "anthropic/claude-opus-4-6" },
        identity: { name: "Work Bot" },
        groupChat: { mentionPatterns: ["@work", "@workbot"] },

        sandbox: {
          mode: "all",              // "off" | "non-main" | "all"
          scope: "agent",           // "session" | "agent" | "shared"
          workspaceAccess: "rw",
        },

        tools: {
          allow: ["read", "exec"],
          deny: ["browser", "cron"],
        },
      },
    ],
  },
}

Read the full file on GitHub · 157 lines

Files

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.

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. 12d ago First seen · 157 lines · 53 tokens per session scan A f330c3280554

Subscribe to this mod's changes

openclaw-multi-agent is a skill published in the GitHub repository TheophilusChinomona/claude-openclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 1,145 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens