Start here
Technical chapter.start-here raw
If you are not a developer. UCC is the setup ZT uses to run agents. An agent is a program on your computer that reads and writes files, keeps notes in a folder that is backed up, builds web pages you can share, and reaches you on Telegram when it needs an answer. Step 0 checks you have ZT's message; steps 1 to 5 set everything up. Each step has one short paragraph, a text to paste to your agent, and a line saying how to check it worked. If a step does not pass, send ZT the step number and what your agent printed.
If you are technical. Five steps on one machine. At the end you have one Claude Code agent the daemon knows by name, a sessions root where everything it writes survives, a bot that reaches you on Telegram, and a wiki your agents grow — with nothing to babysit.
What the steps produce
| Step |
You end up with |
Proof |
| 0 Before you start |
The message from ZT, in hand: this handbook's link, the install line with its three values, the invitation to the private repositories on git.0xdao.app |
the message itself |
| 1 Install |
UCC and the ccc-statusd daemon on your machine, already running |
ccc-statusd status |
| 2 First session |
One Claude Code agent with an eight-character name and a card of its own |
the joined … as agent … banner |
| 3 Sessions root |
The agent's records pushed to your own private GitHub repository every ten minutes |
bin/check prints check: ok |
| 4 Telegram |
Your own bot in a group of your own, so an agent can ask you a question from anywhere |
a test question reaches your group with buttons |
| 5 Wiki |
A wiki that grows from what your agents learn |
mrd run LLM_WIKI.md check passes |
Who "your agent" is in steps 0, 1 and 2
Your UCC agent does not exist until step 2. Until then, "your agent" is whatever AI assistant you already use. Step 0 needs only a chat. Steps 1 and 2 need an assistant that can run commands in a terminal on this computer, such as Claude Code or Codex; if you have none, do those two steps yourself — each is one line typed into the Terminal app, and the step says which. From step 3 on, "your agent" is the UCC agent step 2 started, in the window it opened.
The order
flowchart LR
s1[Install] --> s2[First session] --> s3[Sessions root]
s3 --> s4[Telegram]
s3 --> s5[Wiki]
Do the steps in number order. When step 5 passes, the closing card at the end of this page says where to go next.
Dive in: why this order
Install first: everything after it is a file the installer put on your machine. The first session second: it proves the daemon and its hooks fire before anything depends on them. The sessions root third: from the first session on, every card, memo and result an agent writes lands in that folder. The installer creates it, but it is not durable until step 3 names your repository, and the daemon's sweep reports red every cycle until then. Telegram and the wiki each need only the root; do Telegram first — an agent that cannot reach you stalls on its first question — then the wiki, which graduates from the root.
Dive in: what comes from ZT, and only from ZT
One direct message from ZT carries everything this page cannot: the link to this handbook; the install line, already assembled from your three install values — the username, the token and the ENCRYPTION_PASSWORD; and the invitation to ZT's private code repositories on git.0xdao.app. None of the five steps needs the repositories; the Repos section lists them. Nothing on this page carries a secret, and nothing on it asks you to paste one anywhere except your own terminal, once, in step 1.
Dive in: how a step reads
Every step reads the same way: its title, one short paragraph saying what the step does, then a Tell your agent panel. Its Copy the prompt button copies the whole prompt your agent needs; the last copied line names the web address the prompt lives at, so an agent that can read web addresses re-reads the current text. Under the panel, How to check it worked is what you or your agent run and what a pass prints. The full prompt is folded under The full prompt your agent reads, and the Skill line under it names what the agent loads for the step.
Where next
Technical chapter.where-next raw
Your agent is set up. The next place to go is ccc-pages: a page is a web address with a memory — your agent writes records and files, the page draws them, and anyone you give the link to sees the result. The live examples there include an order sheet, a shift dashboard and a private quote page for one customer, each with the text to paste to your agent to build one like it.
- What you have — what the installer put on your computer, one line per piece.
- Telegram — the group where your bot posts.
- Repos — ZT's code repositories, including the private ones you are invited to.
- Another day — to start an agent again, open a new Terminal window and run the same
ucc-… command as in step 2; any Tell your agent text on this handbook can be pasted into it.
Step 0 — Before you start
Technical step.00-before-you-start raw
Everything you need arrived in one direct message from ZT: the link to this handbook, the install line with your three install values, and an invitation to ZT's private code repositories on git.0xdao.app — that last one is for reading ZT's code later; none of the setup needs it. They come by message because nothing on this page carries a secret. You also need a GitHub account for step 3; make a free one at github.com if you have none. This step only checks that the message is in hand. Your UCC agent does not exist yet, so "your agent" here is any AI assistant you already use — a chat is enough, because nothing runs at this step.
Step 1 — Install
Technical step.01-install raw
One line fetches an installer written for you and runs it without asking a question. When it finishes, your computer has your Claude Code profiles (one command per model ZT gave you), the shared skills, the ccc-statusd daemon that keeps track of your agents, and a sessions root — the folder their work is kept in. The line is yours to run: open the Terminal app (on a Mac: press Command-Space, type Terminal, press Return), paste the install line from ZT's message, and press Return. It asks no questions and ends with ✓ Installation complete!; a FAIL line about sessions.canonical shortly before that is expected — step 3 fixes it. Then close that window and open a new one, so it knows the new commands. "Your agent" here is an AI assistant you already have that can run commands on this computer, such as Claude Code or Codex: it explains the line and reads the output with you, and the install line itself goes only into your own Terminal.
Step 2 — First session
Technical step.02-first-session raw
Open Claude Code in one of the profiles ZT registered for you, sign in if that profile needs it, and send a first message. In a new Terminal window, type ucc- followed by one of your profile names and press Return — the install printed the names at its end, and ucc-profiles lists them. Claude Code opens. If it asks you to sign in, type /login and approve in the browser. Then type hello and press Return: on that first message the daemon gives your agent its name. This window is your UCC agent — from step 3 on, "your agent" means it, and each step's text is pasted here. To start an agent another day, run the same ucc-… command in a new Terminal window. The assistant you used for step 1 can guide this step and prove it.
Step 3 — Make the sessions root durable
Technical step.03-sessions-root raw
The installer made a sessions root — the folder where your agents keep their notes, cards and results — but it is not backed up yet, so every backup cycle refuses on purpose. This step backs it up to a private GitHub repository of yours. You need a free GitHub account; your agent walks you through making an empty private repository there and letting this computer reach it. From then on, everything your agents write is copied to GitHub every ten minutes; files they attach, such as screenshots, stay on this computer until the Second machine section moves them. Paste this step's text into the Claude Code window you opened in step 2.
Step 4 — Telegram
Technical step.04-telegram raw
This step connects a Telegram bot of your own to your agent, so that a question your agent asks in the terminal also reaches your phone as a message with buttons and a tap answers it. You create the bot in Telegram, make a group of your own and add the bot to it; the questions arrive there, seen only by the people you put in that group. Your agent finds the group and wires everything else. If you are already in ZT's team group, you may add the bot there instead, knowing that everyone in it will see your agent's questions.
Step 5 — Your wiki
Technical step.05-wiki raw
This step gives your agents a long-term memory: a folder of plain-text notes, called a wiki, where each piece of work leaves what it learned and later work reads it back. Your agent sets it up from a ready-made starter ZT published and runs the wiki's own check; it asks you only which folder to use — ~/wiki is a good answer.