vladmesh

Codegen Orchestrator — DevOps skill for Claude Code

DevOps community

Multi-agent LangGraph orchestrator: a Telegram brief becomes a deployed project (code, CI/CD, domain, SSL) built by isolated Claude Code / Factory.ai workers.

How to install Codegen Orchestrator

This entry records only its repository, not the path inside it, so there is no exact command to give. Open vladmesh/codegen_orchestrator and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Codegen Orchestrator does

Multi-agent LangGraph orchestrator: a Telegram brief becomes a deployed project (code, CI/CD, domain, SSL) built by isolated Claude Code / Factory.ai workers.

Alternatives in DevOps

Cloudflare Deploy — Deploy apps to Cloudflare using Workers, Pages, and platform services 14.6k ★
Azure Event Grid .net — Event Grid topic and domain publishing 1.8k ★
Cccc — Coordinate your coding agents like a group chat — read receipts, delivery tracking, and remote ops from your p 1.1k ★

README

Codegen Orchestrator

A person describes a project in Telegram. Twenty to thirty minutes later that project is running in production, with a repository, CI, a domain and a certificate. Between those two moments no human touches anything.

The system is a set of agents built on LangGraph. A Product Owner agent runs the dialogue and decides what to build; an architect splits the result into tasks; coding agents in isolated containers write the code; the pipeline puts it through CI, deploy and post-release QA. The user comes back and says "now make it send pictures of cats", and the same machinery extends the running project rather than generating a new one.

Generated projects are built from [codegen-product-kit](https://github.com/vladmesh/codegen-product-kit), a spec-first framework, so the pipeline reasons about a declared contract instead of guessing at free-form code.

How a request flows

graph TD
    User((User)) <--> |Telegram| Bot[Telegram Bot]
    Bot <--> |Redis Stream| PO[Product Owner Agent]

    PO --> |tools| API[API Service]
    PO --> |create story| ArchQueue["architect:queue"]

    subgraph Scheduler
        Dispatcher[Task Dispatcher]
    end

    ArchQueue --> Architect[Architect]
    Architect --> |tasks| API
    Dispatcher --> |"scaffold:queue"| Scaffolder[Scaffolder]
    Dispatcher --> |"engineering:queue"| Eng[Engineering Worker]
    Dispatcher --> |"deploy:queue"| Dep[Deploy Worker]
    Dep --> |"qa:queue"| QA[QA Worker]

    Eng --> |manages| Workers[Coding Agent Containers]

    API --> |data| DB[(PostgreSQL)]
    Eng --> |result| PO
    Dep --> |result| PO
    QA --> |result| PO

A Project has the lifecycle states `draft`, `active`, `paused`, and `archived`. Pipeline activity is represented by its Stories, Tasks, and Runs; queues carry typed contracts between pipeline stages.

Stage by stage: [docs/PIPELINE_V2.md](docs/PIPELINE_V2.md). Agent nodes and their tools: [docs/NODES.md](docs/NODES.md). The queues and DTOs thems