# Agent Workflow System: A Bilingual AI Collaboration Workflow System for Claude Code and Codex

> A bilingual (Chinese/English) AI Agent workflow system that turns vague ideas into executable tasks through 7 collaborative skills, a code of conduct, and a session recovery mechanism, while supporting both Claude Code and Codex CLI platforms.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-06-10T11:15:27.000Z
- 最近活动: 2026-06-10T11:20:46.017Z
- 热度: 161.9
- 关键词: AI Agent, Claude Code, Codex CLI, 工作流系统, 会话恢复, 行为规范, 任务管理, AI协作, 开源工具
- 页面链接: https://www.zingnex.cn/en/forum/thread/agent-workflow-system-claude-code-codex-ai
- Canonical: https://www.zingnex.cn/forum/thread/agent-workflow-system-claude-code-codex-ai
- Markdown 来源: floors_fallback

---

## Agent Workflow System: Bilingual AI Collaboration Workflow for Claude Code & Codex CLI

### Core Overview
Agent Workflow System is an open-source bilingual (Chinese/English) AI agent workflow system developed by 1139030773-cmd and released on GitHub in June 2026. It aims to convert vague ideas into executable tasks via three core mechanisms:
1. 7 specialized collaboration roles forming a PDCA loop
2. 14-chapter code of conduct (behavior norms)
3. Session recovery for cross-session continuity
It supports both Claude Code and Codex CLI platforms, serving as an efficient AI collaboration partner for developers.

Source: [GitHub Repository](https://github.com/1139030773-cmd/agent-workflow-system)

## Background: Pain Points of Current AI Programming Assistants

With the popularity of AI programming assistants like Claude Code and Codex CLI, developers face key challenges:
- Converting vague ideas into AI-understandable explicit tasks
- Maintaining context coherence in multi-round dialogues
- Preventing task drift or scope creep
- Losing context when closing conversation windows
Agent Workflow System is designed to address these issues by introducing structured collaboration mechanisms.

## System Architecture: 7 Roles & 14-Chapter Behavior Norms

### 7 Collaboration Roles
The system decomposes AI functions into 7 roles forming a closed loop:
1. **workflow-system**: Coordinator (route user intent to appropriate skills)
2. **newbie-guide**: Newbie mentor (Socratic questioning to clarify vague goals)
3. **project-master**: Project planner (task breakdown, checkpoint setting)
4. **debug-fixer**: Debugger (TDD-based bug fixing)
5. **learning-coach**: Learning guide (structured learning paths)
6. **drift-auditor**: Drift monitor (alert on scope creep/context drift)
7. **phase-closeout**: Phase finisher (summary, state freezing, recovery token generation)

### 14-Chapter Behavior Norms
Key norms include:
- Role isolation (planners don’t code, executors don’t make architecture decisions)
- 5-level error correction mechanism
- Legal risk early warning (3 layers)
- Artifact handover optimization (50k context →5k lightweight artifacts)
- Task fork/convergence (subtasks inherit parent context)
- 4-question self-check before changes (logic, conflict, importance, timing)

## Innovative Session Recovery: Cross-Session Continuity

Traditional AI assistants lose context when windows close. This system solves it via:
1. **CLAUDE.md auto-detection**: Check for unfinished tasks at session start
2. **RESUME.md + context_snapshot**: Save decision records, user preferences, and notes as checkpoints
3. **Time interval awareness**: Adjust recovery strategy based on time since last session (e.g., detailed review for >24h gaps)
4. **SessionEnd hook**: Auto-save checkpoints and commit changes when window closes
5. **SessionStart hook**: Auto git pull (24h throttle) for code sync
6. **Cross-platform support**: Works with PowerShell and Bash

## Dual Platform Support: Installation for Claude Code & Codex CLI

### Claude Code Installation
- Natural language: Say "Install agent-workflow-system for me" to Claude
- Manual: Clone the repository and copy config files

### Codex CLI Installation
- Command line: `codex plugin install 1139030773-cmd/agent-workflow-system`
- Desktop app: Install via plugin market

## Practical Scenarios & Natural Language Launch Commands

The system supports intuitive natural language activation without complex commands:

| Scenario               | Launch Command                                  |
|-------------------------|-------------------------------------------------|
| Vague idea to tasks     | "Start the newbie guide, help me turn my idea into tasks" |
| Project management      | "Enter project master mode, help me manage this project" |
| Bug fixing              | "Help me fix this bug"                         |
| Learning new skills     | "I want to learn Python, make me a study plan" |
| Check task drift        | "Check if my progress has drifted"             |
| Phase summary           | "Help me do a phase closeout and organize what we did" |

It auto-detects Chinese/English input and adapts accordingly.

## Version Evolution & Open Source Community

### Version Updates
- v1.5.0: Introduced session recovery mechanism
- v1.7.5: Added skill exit protocol and task return format specification

### Community & License
- License: MIT (open source)
- Status: Submitted to Codex community plugin market (waiting PR merge)
- Active update rhythm addressing real user pain points

## Conclusion: New Paradigm of AI Collaboration

Agent Workflow System represents a new AI collaboration paradigm: treating AI as a professional partner with role division, consistent norms, and memory. It ensures:
- Professionalism via role separation
- Consistency via behavior norms
- Continuity via session recovery

For developers using Claude Code or Codex CLI, this system is worth trying—it may transform how you collaborate with AI, turning vague ideas into executable code.