A Chinese-English bilingual AI workflow system for Claude Code and Codex CLI. Turns vague ideas into executable tasks through 7 collaborative skills + behavioral constitution + session recovery. Beginner-friendly.
You don't need to understand how this system works. Just say what you want to do. The AI will guide you step by step — no jargon, no technical background required.
Close the window, the task survives. New window, same AI.
- CLAUDE.md — Auto-detects unfinished tasks on session start
- RESUME.md + context_snapshot — Checkpoint with decisions, preferences, and footgun prevention
- Open-ended recovery — No fixed options; AI presents status, you decide direction
- ⏱️ Time-interval awareness — Adjusts behavior based on how long since last session
- SessionEnd Hook — Auto-saves checkpoint + commits on window close
- SessionStart Hook — Auto
git pullon session start (24h throttle) - Cross-platform — PowerShell + Bash
Step 1: Enable hooks — Add this to your .claude/settings.local.json:
{
"hooks": {
"SessionStart": [{
"matcher": "",
"hooks": [
{"type": "command", "command": "powershell.exe -File .claude/hooks/session-start.ps1", "timeout": 10}
]
}],
"SessionEnd": [{
"matcher": "",
"hooks": [
{"type": "command", "command": "powershell.exe -File .claude/hooks/session-end.ps1", "timeout": 15}
]
}]
}
}Hook scripts are in hooks/ (copy to .claude/hooks/). Both .ps1 and .sh versions available.
Step 2: Run health check — scripts/health-check.ps1 check for system integrity scan.
You change system → Close window → Hook auto commit + push
↓
GitHub updated
↓
User opens window → Hook auto pull
| Skill | Role | When |
|---|---|---|
workflow-system |
Orchestrator | Entry routing to the right sub-skill |
newbie-guide |
Guide | Vague goal → actionable task (Socratic questioning + optional background research) |
project-master |
Planner | Task breakdown, decision gates, acceptance criteria |
debug-fixer |
Executor | Errors / test failures / bugs (TDD minimal fix) |
learning-coach |
Executor | Learning programming, design, languages, etc. |
drift-auditor |
Auditor | Scope creep / context drift / task fork detection |
phase-closeout |
Closer | Phase wrap-up, freeze state, generate resume token |
15-chapter unified behavioral standard governing all skills:
- Role isolation — Planners don't code, executors don't make architectural decisions
- Five-level error correction — From self-check to mandatory human intervention
- Legal awareness — Three-layer risk alerts without giving legal advice
- Artifact handoff — 50k context → 5k artifact for lightweight inter-skill transfer
- Session recovery — Cross-session task continuity
- Task forking & convergence — Sub-tasks anchored to parent task context, auto-return on completion
- Four-question self-check — Before every change: logical? conflicts? important? right timing?
- Time-scale awareness — Tasks track created/last-active timestamps; stale decisions flagged for re-confirmation
CLAUDE.md Rules (v1.6.2 ~ v1.12.1):
- Verify by doing — Run commands, don't guess from docs
- Tone standards — Patient, equal, explain everything; no dismissive one-liners
- Task closeout rule — Never close a task without user confirmation
- Topic layer awareness — Recap what was done and where you stand in natural language
- Four-question self-check — Pre-implementation gate: logic / conflict / importance / timing
- Task registration rule — Every new task must be registered in task_stack before starting
- Task fork & converge — Sub-tasks inherit parent context; auto-return on completion
- Return-to-task format — After drift, resume with: goal / progress / next step
- Time-scale awareness — Real-world timestamps on tasks & decisions; auto-flag stale items after idle periods
Option 1: Ask Claude (Recommended)
In chat:
Install agent-workflow-system for me
Option 2: Manual
git clone https://github.com/1139030773-cmd/agent-workflow-system.git
cp -r agent-workflow-system/.claude ./ && cp agent-workflow-system/CLAUDE.md . && cp agent-workflow-system/RESUME.md .Option 1: CLI One-liner (Recommended)
codex plugin install 1139030773-cmd/agent-workflow-systemOption 2: Desktop App — Install from URL
Settings → Plugins → Menu next to search → Install from URL:
https://raw.githubusercontent.com/1139030773-cmd/agent-workflow-system/main/plugins/agent-workflow-system/.codex-plugin/plugin.json
Option 3: Marketplace (requires PR merge)
codex plugin marketplace add https://github.com/hashgraph-online/awesome-codex-plugins.gitThen type /plugins in chat and find Agent Workflow System.
💡 Marketplace install depends on PR #202. Use Option 1 or 2 in the meantime.
After installation, try one of these:
| Scenario | Say |
|---|---|
| 🆕 Vague idea | "Start the newbie guide, help me turn my idea into tasks" |
| 📋 Manage a project | "Enter project master mode, help me manage this project" |
| 🐛 Something's broken | "Help me fix this bug" |
| 📖 Learn something | "I want to learn Python, make me a study plan" |
| 🔍 Feeling off-track | "Check if my progress has drifted" |
| 📦 Wrap up | "Help me do a phase closeout and organize what we did" |
💡 No commands to memorize. Speak naturally. The system auto-detects your language and intent.
| Version | Date | Highlights |
|---|---|---|
| 1.12.1 | 2026-06-12 | 🛡️ Adversarial verification — independent agent checks for "should've changed but didn't" before release |
| 1.12.0 | 2026-06-12 | 🔍 Research gate — optional background research between newbie-guide and project-master |
| 1.11.1 | 2026-06-12 | health-check.ps1 encoding fix — 3 bugs, 100% health |
| 1.11.0 | 2026-06-12 | PROJECT.md — one-screen overview, auto-updated per phase |
| 1.10.3 | 2026-06-11 | Removed write-level gate — classification interference |
| 1.10.2 | 2026-06-11 | Full distribution — scripts + hooks included in plugin package |
| 1.10.0 | 2026-06-11 | One-click project archive — INDEX.md + NL recall |
| 1.9.2 | 2026-06-11 | Output self-check Q4 + phase-transition auto audit |
| 1.9.1 | 2026-06-11 | Project dashboard — health_score + active_tasks in RESUME.md |
| 1.9.0 | 2026-06-11 | Beginner mode — newbie entry + jargon filter + beginner channel |
| 1.8.2 | 2026-06-11 | Output self-check + write-level gate — prevent dev content leaking into workflow |
| 1.8.1 | 2026-06-11 | System health check + auto-cleanup — integrity scan on every session start |
| 1.8.0 | 2026-06-11 | Multi-window session management — .resume/ per-window files prevent conflicts |
| 1.7.7 | 2026-06-10 | Time-scale awareness — task timestamps + decision expiry + idle detection |
| 1.7.6 | 2026-06-10 | English adaptation — bilingual README + language auto-detect + starter prompts |
| 1.7.5 | 2026-06-09 | Skill exit protocol + Return-to-task format rule |
| 1.7.4 | 2026-06-09 | Mandatory format for drift → task return |
| 1.7.3 | 2026-06-09 | Sub-task anchoring: parent context = practice material |
| 1.7.2 | 2026-06-09 | Task registration rule + background recap on return |
| 1.7.1 | 2026-06-07 | Session closeout reminder + Version consistency validator |
| 1.7.0 | 2026-06-07 | CLAUDE.md split (dev rules / user rules) |
| 1.6.3 | 2026-06-07 | Task closeout rule |
| 1.6.2 | 2026-06-05 | Verify by doing + Tone standards |
| 1.6.1 | 2026-06-05 | Time-interval awareness + 7-step change protocol + Auto-update pipeline |
| 1.6.0 | 2026-06-05 | context_snapshot + Single-thread principle |
| 1.5.0 | 2026-06-05 | Session recovery mechanism, cross-platform hooks |
See CHANGELOG.md for full details.
- GitHub: 1139030773-cmd/agent-workflow-system
- Codex:
codex plugin install 1139030773-cmd/agent-workflow-system - Community Marketplace: awesome-codex-plugins
- 中文文档
MIT