agent-engine

Automate long-running coding across multi-session contexts with structured workflows.

Updated Mar 17, 2026

Search Tags:#testing #development #agent #coding #multi-session #autonomous

Ready to run

npx skills add https://github.com/Blake-John/agent-config --skill agent-engine

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agent-engine
Source: https://github.com/Blake-John/agent-config/tree/main/.zeroclaw/workspace/skills/agent-engine
Command: npx skills add https://github.com/Blake-John/agent-config --skill agent-engine

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

长时间、跨会话的自动化编码任务经常因记忆断裂、上下文窗口限制和缺乏统一的进度追踪而低效。agent-engine 提供两阶段架构（Initializer Agent 与 Coding Agent），实现环境初始化、功能列表管理、增量进度记录、Git 提交规范以及端到端测试的完整工作流。

Core Features & Use Cases

支持环境初始化、特征分解与逐步实现，适用于需要跨越多会话完成的复杂项目。
提供增量进度追踪、会话产物留存与测试，帮助团队维持可追溯性和高质量交付。
通过内置参考示例与产物模板，快速建立开发环境并启动持续开发过程。

Quick Start

在需要进行长时间自主编码任务时，调用 agent-engine 以启动并持续跨会话开发。

Frequently Asked Questions about agent-engine

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I maintain context for autonomous coding across multiple sessions?▼

Autonomous coding across multiple sessions requires a two-phase architecture with initializer and coding agents. This approach provides environment initialization, incremental progress tracking, and cross-session continuity to prevent memory loss during long-running development tasks.

What is the best way to track incremental progress for complex development projects?▼

Incremental progress tracking for complex development projects is best handled through standardized logs and structured workflows. This ensures session artifacts are preserved, feature lists are managed step-by-step, and Git commit standards maintain traceability throughout the lifecycle.

How do I set up an environment for long-running autonomous coding tasks?▼

Setting up an environment for long-running autonomous coding involves configuring a SKILL.md with YAML frontmatter and optional references, scripts, and assets directories. This structure initializes the workspace and establishes standardized prompts for subsequent coding sessions.

Does this multi-session coding approach support end-to-end testing and Git commit standards?▼

Multi-session coding workflows do support end-to-end testing and Git commit standards. The architecture integrates testing into the incremental development cycle and enforces commit conventions to ensure high-quality, traceable delivery across all autonomous sessions.

When should I use a multi-session coding agent instead of a single-session tool?▼

A multi-session coding agent should be used instead of a single-session tool when projects require environment initialization, feature decomposition, and step-by-step implementation that exceed context window limits and need continuous cross-session continuity.