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-user-workspacesgit 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-user-workspaces)<a href="https://agentmods.dev/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-multi-user-workspaces"><img src="https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-multi-user-workspaces/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-user-workspaces"><img src="https://agentmods.dev/badge/skills/theophiluschinomona/claude-openclaw-plugin/openclaw-multi-user-workspaces.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 | $0.00059 | $0.02890 |
| Opus 5 | $0.00030 | $0.01445 |
| Sonnet 5 | $0.00012 | $0.00578 |
| Haiku 4.5 | $0.00006 | $0.00289 |
Grade A, and why
openclaw-multi-user-workspaces 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 10d 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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenClaw Multi-User Workspaces
Guide the user through setting up a gateway so multiple people can share it safely — with isolated sessions, controlled access, and appropriate security boundaries.
Trust Model
OpenClaw is a personal assistant, not a multi-tenant bus. Understand what's safe before sharing.
| Scenario | Recommendation |
|---|---|
| Family (3-5 people, full trust) | Single gateway, session isolation, one sandboxed agent, pairing policy |
| Small team (5-10, cooperative) | Single gateway, per-user agent routing, sandbox + tool restrictions |
| Company team (same trust boundary) | Single gateway on dedicated machine/user, tiered agents, strict tool policy |
| Adversarial users (competing, untrusted) | Separate gateways — ideally separate OS users/hosts per trust boundary |
If users are adversarial to each other, a single gateway is not a supported security boundary. See references/security-guide.md for the full decision tree.
Step 1: Session Isolation
Set session.dmScope to prevent users from seeing each other's conversations:
| Value | Behavior | When to use |
|---|---|---|
"main" (default) |
All DMs share one session | Single-user only |
"per-peer" |
One session per sender (across channels) | Simple multi-user |
"per-channel-peer" |
One session per channel + sender pair | Recommended for multi-user |
"per-account-channel-peer" |
One session per account + channel + sender | Multi-account channels |
{
session: {
dmScope: "per-channel-peer",
},
}
This is a messaging-context boundary, not a host-admin boundary. It prevents cross-user context leakage in conversations but does not isolate host-level file access.
If the same person contacts you on multiple channels, use session.identityLinks to collapse their DM sessions into one canonical identity.
Step 2: User Access Control
DM Policy
Each channel has a dmPolicy that gates inbound DMs before messages are processed:
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.
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.
- 10d ago First seen · 358 lines · 59 tokens per session scan A deecce44ed14
openclaw-multi-user-workspaces is a skill published in the GitHub repository TheophilusChinomona/claude-openclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 59 tokens to every session and 2,890 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…