duolabmeng6 GitHub avatar

AICodeCoreWorkflow

duolabmeng6

A reusable skill for Claude Code and Codex that enforces a structured code modification workflow: Research, Ideate, Plan, Approve, Execute, Review.

Stars

82

7-day growth

No data

Forks

11

Open issues

1

License

No data

Last updated

2026-07-17

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It bridges two major AI coding agents (Claude Code and Codex) with a unified, approval-gated workflow, promoting disciplined code changes and reducing risk.

Who it is for

  • Developers using Claude Code or Codex for automated code editing
  • Teams that want a standardized, reviewable process for AI-driven code changes
  • Engineers seeking to enforce a plan-before-execution gate in their AI coding workflow
  • Open-source maintainers wanting to share a reusable skill across different agent ecosystems

Use cases

  • Implementing new features with a structured plan and approval step
  • Refactoring existing code while maintaining scope and risk awareness
  • Making complex cross-file modifications that require human oversight
  • Onboarding new developers to a consistent AI-assisted change process

Strengths

  • Cross-agent compatibility (Claude Code and Codex) out of the box
  • Automatic invocation based on task type, minimizing manual setup
  • Mandatory plan approval gate that locks scope without freezing implementation details
  • Simple installation via a single natural language command

Considerations

  • Requires the agent to support the Skill system (Claude Code or Codex with skills)
  • Manual installation fallback needed if auto-install fails, potentially requiring file copying
  • Only applicable to tasks intending code modifications, not to general Q&A or read-only reviews

README quick start

安装

Description

编程核心工作流2.0

Related repositories

Similar projects matched by category, topics, and programming language.

MoonshotAI
Featured
MoonshotAI GitHub avatar

Kimi-K3

Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.

AI & Machine LearningAI Agents
3,348
xuchonglang
Featured
xuchonglang GitHub avatar

investing-for-beginners

A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.

Blockchain & Web3
2,739
Krishnagangwal
Featured
Krishnagangwal GitHub avatar

CS-Fundamentals

A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.

Data & DatabasesDatabases & Storage
2,326