Archived plugin

We built this plugin. Then we killed it.

Agent-to-agent harnesses burn tokens out of all proportion to what they hand back. We watched it happen to our own, so we stopped shipping it and said why.

Why it stopped

The overhead outran the payoff.

Published work points the same way, though none of it is about this plugin specifically. Anthropic, whose harness this plugin extended, wrote up their own multi-agent system in June 2025 and said that "most coding tasks involve fewer truly parallelizable tasks than research, and LLM agents are not yet great at coordinating and delegating to other agents in real time." The same write-up puts multi-agent systems at about 15 times the tokens of a plain chat, and it reports a 90.2% improvement over a single agent on their research eval. The overhead is real, and so is the payoff on work that parallelizes. A plugin that walks one person through one install is not that work.

That applies to the paid OpenClaw setup session we used to sell as well. We stopped offering it for the same reason, and we would rather say so here than let it disappear without a word.

Still true
You can clone the repo and read the skills in it. Nothing has been taken down.
Not true anymore
No new platforms, and no fix when OpenClaw changes underneath it. We are not shipping another version that tracks OpenClaw releases.

This is our read on our own plugin, not a verdict on OpenClaw, which is somebody else's project. If you are here because your install is broken, we are not the ones to fix it anymore. OpenClaw's own docs are linked at the bottom of this page, and everything we wrote about the plugin is still below.

Want this built for your business, or have an idea that needs AI?

Work with us

What it was

A Claude Code plugin for running OpenClaw.

OpenClaw is a local AI gateway that connects Claude to messaging apps like Slack, WhatsApp and Telegram. This plugin turned Claude Code into an OpenClaw expert: install, configure, troubleshoot and harden, through an onboarding wizard that interviewed you and wrote a deployment plan across 21 messaging platforms.

What the plugin shipped

  • Onboarding Wizard

    Interactive interview that generates a personalized deployment plan

  • 21 Channels

    Native and plugin-based support for Slack, Teams, Signal, Matrix, and more

  • Provider-Neutral Models

    Anthropic, OpenAI, Ollama (free/local), xAI, Kilo Code, and more

Shipped

Interactive onboarding

Run /onboarding and the plugin interviews you about your use case, preferred channels, operating environment, security needs, and model provider preference. It then generates a personalized deployment journey.

Journey templates

  • Personal Assistant
  • Family / Team
  • Enterprise
  • Developer
  • Docker / K8s
  • Upgrader
  • Public Chatbot

Capabilities

  • Onboarding Wizard

    Interactive interview that asks about your goals, channels, environment, and security needs, then generates a personalized setup journey with specific milestones and commands.

  • Fresh Install

    Guided setup across macOS, Linux, Windows (WSL2), Docker, and Kubernetes with prerequisite validation.

  • Channel Setup

    Configuration for 21 platforms: Slack, WhatsApp, Telegram, Discord, BlueBubbles, Signal, Google Chat, Teams, Matrix, Feishu/Lark, LINE, Mattermost, and more.

  • Troubleshooting

    Structured diagnostics with config validation, version checks, and platform-specific fixes.

  • Security Hardening

    15-point security checklist, CVE awareness, tools profiles, SecretRef secrets management, sandbox configuration.

  • Automation

    Cron jobs, Gmail webhooks, sub-agents, scheduled workflows.

  • Model Configuration

    Provider-neutral setup for Anthropic, OpenAI, Ollama (local/free), Kilo Code, xAI/Grok, Moonshot, MiniMax, Vercel AI.

  • PDF Analysis

    Built-in PDF tool with configurable providers and size limits.

  • Docker / K8s

    Health endpoint configuration, disk budgets, container-optimized deployment.

  • Skills & Plugins

    ClawHub skill registry (3,200+ skills), official plugin management.

Supported messaging platforms

Native (built-in)

  • Slack
  • WhatsApp
  • Telegram
  • Discord
  • BlueBubbles (iMessage)
  • Signal
  • Google Chat
  • IRC
  • WebChat

Plugin-based

  • Feishu / Lark
  • Microsoft Teams
  • Matrix
  • LINE
  • Mattermost
  • Nostr
  • Nextcloud Talk
  • Synology Chat
  • Tlon
  • Twitch
  • Zalo
  • Zalo Personal

How it worked

01/openclaw-manager

Core management

Install, configure, troubleshoot, and harden your OpenClaw deployment. Covers channels, security, automation, models, and infrastructure.

02/onboarding

Onboarding wizard

Guided interview that builds a personalized deployment plan tailored to your use case, environment, and preferred channels.

Still installable

Install in one command

Install the plugin directly from GitHub and let Claude Code guide you through setup.

claude plugin install github:ClariSortAi/openclaw-manager-plugin

Requires OpenClaw v2026.3.1 at minimum.

The paid part

Here is what we sell.

Everything above this line is free and stays free. Below it is what we sell. The prices are the prices, and the two subscriptions carry 30 days money back on the first month.

Line chart of views by the hour for our five newest Reels, on a log scale. Two climb fast in the first hours. Three level off in the low thousands.
A real dashboard Claude built from our own account through the Analyzer. Last updated 15 October.

Mica Social Media Analyzer

Price: $29/ month

Your Instagram, answered by the ChatGPT or Claude you already use. Connect the account once, then ask in plain words what worked and what to post next.

You post on Instagram and you are done guessing from the Insights tab.

  • Which Reels held attention, ranked, without opening Insights
  • Readings at 1, 24 and 72 hours after every post, so you see what happened while it was moving
  • Next captions written in the style of your most saved posts
  • Read only. It never posts or changes anything

7 days free with a card on file. About a dollar a day after that.

Start 7 days free

30 days money back on the first month. Email guru@graniteai.co and we refund it.

Nine Instagram posts from an insurance agency in New Hampshire, one a day from 8 to 16 October. Fall scenes with headlines about crash calls, home rebuild costs, renewals and a customer review.
The Instagram feeds of two Mica Social customers, captured 16 October. Mica wrote, designed and published every post shown, one a day.

Mica Social

Price: $49/ month

An AI that writes, designs, checks and publishes a post to your Facebook and Instagram every day. You send a photo when you have one. It does the rest.

You know the feed should be alive every day and it is not.

  • A finished post every day, with a photo made for it. Nothing to shoot
  • Timed to your local weather, season and county numbers
  • Five checks before anything publishes. No approvals, no calendar, no logins
  • Every photo you send becomes its own extra post

An agency running a daily feed bills $500 to $1,500 a month. 3 days free with a card on file.

See Mica Social

30 days money back on the first month. Email guru@graniteai.co and we refund it.

The readiness audit, done for you

Price: $349One week

Send us access to your repo. We run the nine-lane review, change nothing, and hand back the report with a 30 minute call on the three gaps to close first.

You have a product you charge for, or want to, and you would rather read the verdict than run the agents.

  • The report at docs/commercial-readiness.md: a verdict, a scorecard, every gap with the file to open and how to verify it
  • Legal, security, billing, support, marketing, operations and the rest, checked at once
  • A 30 minute call on the three gaps to close first
  • Nothing in your repo changed. The workflow prompt is yours to run afterward

The review is the one in the video. On our own product it found 87 gaps. The overnight run that followed was 148 commits and one pull request.

If the review finds no gap worth your time, you pay nothing.

The guided first run

Price: $9960 minutes

We run the review on your repo together, on a call, and you leave with the report in your repo and the three gaps to close first.

You have the kit and a repo, and you would rather do the first run with someone who has done it.

  • The review running on your machine, in your Claude Code
  • The verdict read together, and the three gaps picked
  • The workflow prompt set up so you can run it that night
  • The call recording

New. You would be one of the first. The run itself is the one in the video: 190 agents, 148 commits, one pull request.

If the review will not run on your setup during the call, there is no charge.

GraniteAI builds and runs AI systems for small and midsized businesses, out of Manchester, New Hampshire.

What we build instead

We stopped building bridges between other people's products and started building the context that goes into the model. Same idea, fewer moving parts, nothing that breaks when somebody else ships a release.