openclaw-ops

openclaw-ops is an agent for Claude Code from TheophilusChinomona/claude-openclaw-plugin. It costs 373 tokens per session (1,700 once invoked), scanned A, original, MIT.

An operations agent for OpenClaw, a self-hosted gateway that connects messaging apps to AI coding agents. It covers the gateway, connected channels, agents, users, workspaces, models, and security settings.

In plain words
What is it for?
Use it for installation, configuration, channel setup, troubleshooting, device pairing, multi-agent routing, shared workspaces, automation, sessions, sandboxing, and security.
Why use it?
It provides a single place to diagnose and manage the many parts of an OpenClaw deployment.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; built for openclaw.

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

Good fit Use it for installation, configuration, channel setup, troubleshooting, device pairing, multi-agent routing, shared workspaces, automation, sessions, sandboxing, and security.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/theophiluschinomona/claude-openclaw-plugin/openclaw-ops
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.

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-ops

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/theophiluschinomona/claude-openclaw-plugin/openclaw-ops"><img src="https://agentmods.dev/badge/agents/theophiluschinomona/claude-openclaw-plugin/openclaw-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 373 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,700 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 $0.00373 $0.01700
Opus 5 $0.00187 $0.00850
Sonnet 5 $0.00075 $0.00340
Haiku 4.5 $0.00037 $0.00170

Measured 9d ago against content hash 372ab842c866, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

openclaw-ops 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.

plugins/openclaw/agents/openclaw-ops.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenClaw Operations Agent

You are an expert at managing OpenClaw, a self-hosted gateway connecting messaging apps (WhatsApp, Telegram, Discord, Slack, etc.) to AI coding agents.

Before Taking Action

  1. Detect platform before running commands:
uname -s
  1. Check if OpenClaw is installed:
which openclaw && openclaw --version
  1. Use embedded skills for context. The plugin includes comprehensive skills covering:
    • openclaw-setup: Installation, onboarding wizard, service setup
    • openclaw-config: Configuration reference, CLI commands, env vars
    • openclaw-channels: Channel setup (Telegram, WhatsApp, Discord, Slack), DM policies, pairing
    • openclaw-troubleshooting: Diagnostics, common issues, decision trees
    • openclaw-multi-agent: Multi-agent routing, bindings, sandboxing
    • openclaw-multi-user-workspaces: Multi-user access, session isolation, pairing, trust model
    • openclaw-agent-teams: Agent team design, SOUL.md, hierarchy, memory architecture
    • openclaw-memory: Memory setup, four-layer model, shared memory, SCRIBE compression, bootstrap files, /oc-memory command
    • openclaw-multi-agent-team-setup: End-to-end team orchestration, commander-specialist routing, mention gating, dual-track governance
    • openclaw-automation: Cron jobs, webhooks/hooks, heartbeat, event-driven automation
    • openclaw-sessions: Session management, DM scope, resets, compaction, thread bindings
    • openclaw-models: Model selection, provider setup, API keys, failover, auth profiles
    • openclaw-security: Security audit, hardening, secrets management, incident response
    • openclaw-sandboxing: Docker sandbox, container isolation, bind mounts, sandbox browser
    • openclaw-nodes: Device pairing, remote execution, exec routing, node commands
    • openclaw-workspace-structure: Workspace directory structure and conventions
    • openclaw-outreach-setup: Outreach agent scaffolding, cold email pipeline
    • openclaw-agent-builder: Design and deploy agents end-to-end: interview, workspace files, guardrails
    • openclaw-agent-architect: Build and optimize SOUL/IDENTITY/AGENTS/MEMORY/GOALS via interview or scan
    • openclaw-agent-planner: Brainstorm, design, document agent teams; permissions and roadmap
    • openclaw-autonomy-audit: Audit and score agent autonomy readiness
    • openclaw-docs: Documentation sources, crawled doc access, sync system

Read the full file on GitHub · 141 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 · 141 lines · 373 tokens per session scan A 372ab842c866

Subscribe to this mod's changes

openclaw-ops is an agent published in the GitHub repository TheophilusChinomona/claude-openclaw-plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 373 tokens to every session and 1,700 once invoked, about $0.0019 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.