long-running-agent

Coordinates multi-session software development tasks with Git, ensuring consistent progress tracking and workflow continuity across interruptions and agent changes.

Updated Jan 4, 2026

Search Tags:#orchestration #long-running #session-management #initializer #progress-tracking #agent-framework

Ready to run

npx skills add https://github.com/refly-ai/skill-to-workflow --skill long-running-agent

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: long-running-agent
Source: https://github.com/refly-ai/skill-to-workflow/tree/main/skills-source/zijiebijiben/long-running-agent
Command: npx skills add https://github.com/refly-ai/skill-to-workflow --skill long-running-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

Long-running AI agents require persistent state across multiple sessions, enabling them to work on multi-hour or multi-day projects without losing progress.

Core Features & Use Cases

Initializer Agent: sets up the environment, creates progress and feature-tracking artifacts, and boots the workflow for subsequent sessions.
Coding Agent: performs incremental work with session awareness, reads progress, tests, and commits changes between sessions.
Session Startup Sequence: a repeatable sequence to inspect the repo, review progress, and initialize the environment for the next feature.
Progress & Handoff: centralizes context via claude-progress.txt, feature_list.json, and init.sh to enable clean handoffs between sessions.
Use Case: teams building long-running AI projects that must maintain state over time and across sessions.

Quick Start

Run the two-agent workflow: initialize with the Initializer Agent, then proceed with Coding Agent sessions. Before each session, follow the session startup steps: pwd, cat claude-progress.txt, cat feature_list.json, git log --oneline -20, ./init.sh, run a basic test, select the next feature.

Frequently Asked Questions about long-running-agent

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

FAQPage Schema

How do I maintain AI agent state across multiple context windows for long-running tasks?▼

Maintaining AI agent state across multiple context windows requires persistent session management that tracks progress and handles handoffs. Using an initializer agent to set up artifacts like progress files enables work to resume seamlessly on multi-hour coding projects.

What is the best way to structure session handoffs for multi-hour AI coding projects?▼

Structuring session handoffs for multi-hour AI coding projects involves centralizing context using artifacts like progress tracking files and feature lists. A repeatable session startup sequence inspects the repository, reviews progress, and initializes the environment before selecting the next feature.

How do I set up an AI agent workflow to track incremental coding progress between sessions?▼

Setting up an AI agent workflow to track incremental coding progress between sessions involves running a two-agent workflow: initialize the environment with an initializer agent, then proceed with a coding agent that reads progress, tests, and commits changes between sessions.

Can I use a single AI agent to both initialize the environment and perform incremental coding work?▼

Using a single AI agent to both initialize the environment and perform incremental coding work is not recommended. A two-agent workflow separates environment setup and progress tracking from the actual coding agent, ensuring persistent state and clean handoffs across multiple sessions.

What steps should I follow to resume a long-running AI coding task in a new session?▼

To resume a long-running AI coding task in a new session, follow a repeatable session startup sequence: inspect the repository path, review the progress text file, read the feature list JSON, check recent git logs, run the initialization script, execute a basic test, and select the next feature.