ZCode AI Agent Team
The first three steps covered installation, core capabilities, and model configuration. This step installs specialist agents so different models can work as a team. Allow about 5–10 minutes.
⬅️ Previous step · Step 3: Configure Plans and Models prepared your everyday model. The team can make fuller use of role specialization when you have several models with different capabilities.
What It Is
A basic workflow asks one model to do everything from start to finish. An AI agent team assigns production, review, execution checks, and final acceptance to separate specialist roles.
It becomes more professional through defined roles and acceptance criteria, and more intelligent through task routing and model matching—not because installation changes the underlying models.
Why Multiple Models
Different models are strong at different kinds of work. Matching models to roles is more effective than forcing one model to handle every task.
| Model strength | Best suited to | Example roles |
|---|---|---|
| Strong reasoning | Architecture, difficult problems, complex planning | coder-gpt, seoer |
| Fast and economical | Routine checks and frequent lightweight work | verifier, tijian, shencha-final |
| Image understanding | Screenshots, pages, and visual review | shencha-ui, frontend |
| Long context | Large repositories, long briefs, distributed evidence | coder-kimi |
| Strong writing | SEO, outreach, and social content | writer-pro, outreach, sheyun |
The GitHub repository also compares the practical results of single-model and multi-model setups. Beginners do not need many providers on day one: two or three models with different strengths are enough to improve the separation of production, review, and visual work.
The team still works with one model. If you completed Step 3 with two or three models from different capability groups or providers, you can better separate production from review while covering reasoning, speed, and image input.
What You Get
This guide was checked against v2.0.0 on September 7, 2026. The package is currently named Foreign Trade AI Team and includes 20 roles. Future releases may add more, so treat the repository's current README as the source of truth.
| Group | Roles | Main work |
|---|---|---|
| Engineering | coder, coder-gpt, coder-ds, coder-kimi, frontend | Daily implementation, hard problems, alternatives, long context, and front-end work |
| Content and diagrams | writer, writer-pro, mermaid | Regular writing, complex content, and business flowcharts |
| B2B growth | seoer, huoke, outreach, jiankong, sheyun | SEO, lead research, outreach copy, competitor monitoring, and social content |
| Review and verification | shencha, shencha-content, shencha-ui, verifier, shencha-final, tijian | Engineering, content, visual, runtime, final, and website checks |
| Repository governance | github | Read-only review and improvement suggestions for public GitHub repositories |
Creating one agent manually requires a name, model, tools, system prompt, and options such as injecting AGENTS.md. This package predefines the roles and boundaries, so beginners do not need to create all 20 agents one by one.
Before Installation
Confirm the following:
- You completed ZCode Steps 1–3;
- ZCode is version
3.10.2or later; - at least one enabled model can complete a normal conversation;
- Git is installed;
- Python
3.9or later is installed; - Windows users also have PowerShell
5.1or later.
If you do not know whether Git or Python is installed, continue. ZCode will check the prerequisites first and report anything missing.
1. Open the Repository
Open:
Check the version shown near the top, then find 3-Step Automatic Installation. The latest release verified for this guide was v2.0.0. If the repository shows a newer release, follow the repository's current instructions.
2. Copy the Install Prompt
Under 3-Step Automatic Installation in the repository README, you will find one complete installation prompt:
- Start with the sentence asking ZCode to install the agent package;
- copy the entire code block, not only the repository URL;
- do not change the paths, version, or variables.
When you reach the section shown below, click the copy button in the upper-right corner of the code block. The block can scroll horizontally, so you do not need to select the prompt line by line.
The installation prompt is tied to a release tag and role count. Always copy it from the current GitHub README instead of an old article or chat log.
3. Send It to ZCode
Return to ZCode, create a new conversation, and send the complete prompt.
ZCode will work through this sequence:
Check the system, Git, and Python
→ fetch a fixed release
→ identify configured model capabilities
→ assign models to specialist roles
→ preview installation
→ install and report roles, models, and capability fallbacks
If ZCode reports missing Git, Python, or a usable model, address that item and retry. If it finds an existing role or local modification, read the conflict and proposed handling before continuing instead of repeatedly overwriting the installation.
4. Start a New Session
After installation finishes, create another new ZCode conversation. Agents are normally loaded when a session starts, so the old conversation may not show them immediately.
You do not need to reinstall ZCode or add each role manually.
5. Check the Roles
Open:
Lower-left gear → Settings → Agents
Check three things:
- the specialist roles appear in the installed list;
- each role shows its assigned model;
- the toggle on the right is enabled.
The screenshot shows 20 installed roles assigned across GLM, DeepSeek, GPT, Kimi, and Gemini models. The total of 22 at the top also includes two agents that already belonged to the user, so use the “20 installed” count when checking this package.
Start Using the Team
Beginner Prompt
Copy this for the first task:
I have installed the AI agent team. First decide which specialist roles this task needs and give me a short collaboration plan that explains each role. Use different roles for production and review when practical. Then execute the plan and summarize the result.
My task: describe your task here.
The main agent can route the task to suitable roles. You can also name a workflow directly.
Coding Workflow
Ask coder to implement this fix, shencha to perform a static engineering review, verifier to run execution checks, and shencha-final to complete the final acceptance review.
Content Workflow
Ask seoer to create an evidence-based topic brief, writer to produce the draft, shencha-content to check facts, search intent, and conversion flow, and shencha-final to complete the final acceptance review.
B2B Workflow
Ask huoke to identify and verify target companies, then ask outreach to produce market-appropriate outreach copy with evidence grades and recommended next steps.
outreach creates outreach content; it does not mean the message has already been sent. Use the relevant sending tool and confirmation step when you are ready to send.
Diagram Workflow
Here is my business description. Ask mermaid to turn the complete process into a flowchart, with decision branches and manual steps clearly marked.
Model Assignment
The recommended adaptive installation reads a sanitized model capability inventory and assigns models to roles. It uses details such as model name, context capability, and image-input support, so you do not need to select a model for every role manually.
You can update the mapping later:
- add or enable a model in ZCode Model Settings;
- return to the repository README and copy the update prompt for the current release;
- explicitly ask ZCode to remap the models;
- create a new session and check the role list again.
“More intelligent” means task routing, model matching, role specialization, and staged acceptance checks. It does not mean the package retrains or changes the underlying models.
Can One Model Work?
Yes. All 20 roles can still be installed with one model, and their responsibilities and workflow remain available.
However, several benefits become weaker:
- parallel alternatives lack real model diversity;
- production and review may share the same reasoning habits;
- visual roles may not have image-input capability;
- long-context and high-frequency lightweight tasks cannot be separated by capability and cost.
Beginners do not need many providers on day one. Start with the built-in model from Step 3, then add a strong-reasoning or vision model when a real task needs it.
Troubleshooting
Roles Are Missing
Create a new ZCode session, then check Settings → Agents. If the roles are still absent, return to the installation conversation and confirm whether it actually reported completion or stopped at a prerequisite or conflict check.
A Model Is Unavailable
If a role reports that its model or provider is unavailable:
- confirm that the provider is enabled under Model Settings;
- test the model in a normal new task;
- use the current repository README's update prompt to remap the roles.
The Count Is Different
Check the repository's current release first. This guide covers 20 roles in v2.0.0; later releases may add roles. The total at the top may also include agents you created yourself, so compare the installation report and installed list instead.
Completion Check
- You copied the complete installation prompt from the current GitHub README;
- ZCode reported a completed installation and model assignment;
- you created a new session to load the roles;
- the installed roles and their models appear under Settings → Agents;
- a simple task completed a production → review → verification/final-check workflow.
🎉 You have completed the four-step ZCode beginner path. You now have more than a single chat model: you have a professional AI collaboration workflow that can route work across specialist roles.