OpenViSTAI · Agents · Blockchain · Crypto
Menu
Workflow Agents

AI Native Sdlc

AI Native Sdlc is a reusable software-development workflow for Codex and Claude Code, provided as a skill and, for Codex, a plugin. It guides a coding agent from a project goal through planning, design, building, testing, deployment and maintenance, with human approval gates at handoffs.

Independent OpenViST project profile, based on linked sources.

AI Native Sdlc — OpenViST project profile in Workflow Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when adopting a structured, reusable lifecycle for coding-agent work, especially when planning, review and release need explicit human approval points.

Who it is for

  • Developers using Codex or Claude Code who want a staged process for agent-assisted software delivery.
  • Teams that want to fork reusable workflow templates and adapt them to organizational standards.
  • Teams exploring an agent organization with defined roles and peer review.

Documented uses

  • Turn a project idea into an initial workflow and intent artifact.
  • Guide an agent through planning, design, implementation and testing in stages.
  • Make human approval part of handoffs, including the production release gate.
  • Adapt reusable templates and scaffolding to an existing project or team process.
Before you choose

Requirements & limits

The repository is public and MIT-licensed. The README documents skill installation paths for Codex and Claude Code and a Codex plugin option.

  • The workflow treats stages as a directed graph, with artifacts, approval gates and triggers rather than only a fixed linear pipeline.
  • The agent is described as stopping at the production gate; human judgment remains part of approval and release decisions.
  • The repository includes a project initializer and documents an agent-organization scaffold with roles and peer review.
  • Codex and Claude Code use different documented skill locations and repository-memory conventions.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the workflow as a Codex skill

Copy the reusable skill into Codex’s skills directory so it is available to a coding agent.

Before you start

  • A copy of the repository or its skills/ai-native-sdlc/ folder.
  • A shell environment with the documented mkdir and cp commands.

Steps

  1. Create ~/.codex/skills if needed.

  2. Copy skills/ai-native-sdlc into ~/.codex/skills/.

Expected outcome

The skill folder is installed at the documented Codex skills path.

Guide limitations

  • This covers copying the skill only; it does not document a verification step or demonstrate a run.
  • The README also describes a Codex plugin installation path; choose one rather than copying the skill as well when installing the plugin.
Source-based practical guide

Initialize a project workflow

Create the repository’s documented initial workflow scaffold for a named project.

Before you start

  • Python 3, as used in the documented command.
  • A copy of the repository containing skills/ai-native-sdlc/scripts/init_workflow.py.

Steps

  1. Run the command below, substituting the desired project directory and name.

    Documented command
    python3 skills/ai-native-sdlc/scripts/init_workflow.py my-project --name "My idea"
  2. Tell the coding agent to start with the intent, following the README’s example prompt.

Expected outcome

The documented flow has the agent interview the user, write and commit an intent, and request acceptance before proceeding through later gated stages.

Guide limitations

  • The README describes the expected workflow but does not provide a tested result for a specific project.
  • Later stages require human approval at their gates.
Evidence and transparency

Sources & review

Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
bashebr/ai-native-sdlc · Official homepage title · retained in its source language