looper-go-dev — autonomous AI loop runner looper-go-dev, looper-go, community, autonomous AI loop runner, ide skills, looper-go-dev install, looper-go-dev for AI agents, Go implementation for AI loops, looper-go-dev documentation, Claude Code, Cursor

v1.0.0
GitHub

About this Skill

Ideal for Go-based AI Agents needing autonomous loop runner capabilities for streamlined development workflows. looper-go-dev is a Go-based skill for implementing autonomous AI loop runners, providing a structured approach to agent development and configuration.

Features

Provides a CLI entry point through cmd/looper/
Supports configuration loading via internal/config/
Includes agent runners in internal/agents/
Manages task files with internal/todo/
Utilizes prompt templates in internal/prompts/
Handles logging through internal/logging/

# Core Topics

nibzard nibzard
[4]
[0]
Updated: 3/2/2026

Agent Capability Analysis

The looper-go-dev skill by nibzard is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for autonomous AI loop runner, looper-go-dev install, looper-go-dev for AI agents.

Ideal Agent Persona

Ideal for Go-based AI Agents needing autonomous loop runner capabilities for streamlined development workflows.

Core Value

Empowers agents to orchestrate complex workflows using Go implementation, leveraging configuration loading, agent runners, and task file handling through protocols like CLI entry points and internal logging mechanisms.

Capabilities Granted for looper-go-dev

Automating AI loop runner tasks for enhanced efficiency
Generating prompt templates for customized AI interactions
Debugging autonomous AI systems using internal logging facilities

! Prerequisites & Limits

  • Requires Go programming language proficiency
  • Limited to autonomous AI loop runner workflows
  • Dependent on internal configuration and agent runner implementations
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

looper-go-dev

Install looper-go-dev, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Looper-Go Development

Overview

Looper-Go is a Go implementation of the autonomous AI loop runner. This skill covers common development workflows.

Project Structure

looper-go/
├── cmd/looper/          # CLI entry point
├── internal/
│   ├── config/          # Configuration loading
│   ├── agents/          # Agent runners
│   ├── loop/            # Main orchestration
│   ├── todo/            # Task file handling
│   ├── prompts/         # Prompt templates
│   ├── logging/         # JSONL logging
│   └── hooks/           # Post-iteration hooks
├── prompts/             # Bundled prompt templates
└── to-do.json           # Task file (runtime)

Common Commands

Build

bash
1# Build binary 2go build ./cmd/looper 3 4# Build to custom location 5go build -o ~/bin/looper ./cmd/looper 6 7# Build for multiple platforms 8go build -o bin/looper-linux ./cmd/looper 9GOOS=darwin go build -o bin/looper-macos ./cmd/looper 10GOOS=windows go build -o bin/looper.exe ./cmd/looper

Test

bash
1# Run all tests 2go test ./... 3 4# Run with coverage 5go test -cover ./... 6 7# Run specific package 8go test ./internal/loop 9 10# Verbose output 11go test -v ./internal/loop 12 13# Run make test (includes smoke tests) 14make test

Run

bash
1# Default run (uses to-do.json in current dir) 2looper run 3 4# Specify max iterations 5LOOPER_MAX_ITERATIONS=5 looper run 6 7# Run with specific task file 8looper --task-file path/to/tasks.json run 9 10# View logs 11looper tail 12 13# List tasks 14looper ls 15 16# Show config 17looper config 18 19# Check dependencies 20looper doctor

Debug

bash
1# Enable debug logging 2LOOPER_DEBUG=1 looper run 3 4# View JSONL logs 5looper tail 6 7# View specific run 8looper tail --run <run-id> 9 10# Validate task file 11looper validate 12 13# Format task file 14looper fmt

Development Workflow

1. Make Changes

Edit code in internal/ or cmd/ as needed.

2. Test Changes

bash
1# Run unit tests 2go test ./... 3 4# Run smoke tests 5make test 6 7# Run live test 8~/.codex/skills/looper-live-test/scripts/run-live-test.sh

3. Commit Changes

bash
1# Check status 2git status 3 4# Run pre-commit hooks (if installed) 5pre-commit run --all-files 6 7# Commit 8git commit -m "feat: description"

4. Build and Install

bash
1# Build 2go build ./cmd/looper 3 4# Install to PATH 5go install ./cmd/looper

Configuration

Config File Locations (priority order)

  1. .looper/config.json - Project-specific
  2. ~/.config/looper/config.json - User config
  3. Environment variables (LOOPER_*)
  4. CLI flags

Example Config

json
1{ 2 "max_iterations": 100, 3 "agent": { 4 "type": "claude", 5 "model": "claude-3-5-sonnet-20241022" 6 }, 7 "paths": { 8 "log_dir": "./looper-logs" 9 } 10}

Key Environment Variables

VariablePurpose
LOOPER_MAX_ITERATIONSMax loop iterations
LOOPER_DEBUGEnable debug logging
LOOPER_AGENT_TYPEAgent type (codex, claude)
LOOPER_TASK_FILEPath to task file
CODEX_JSON_LOGCodex JSON log mode (legacy)

Troubleshooting

Build Fails

bash
1# Clean and rebuild 2go clean -cache 3go mod tidy 4go build ./cmd/looper

Tests Fail

bash
1# Run verbose to see details 2go test -v ./... 3 4# Check specific package 5go test -v ./internal/loop

Agent Not Found

bash
1# Check config 2looper config 3 4# Verify agent binary exists 5which codex 6which claude 7 8# Check in config 9cat .looper/config.json | jq '.agent'

Adding New Features

1. Add Internal Package

bash
1mkdir internal/feature 2# Create feature.go

2. Add Tests

bash
1# Create feature_test.go 2go test ./internal/feature

3. Wire Into Loop

Edit internal/loop/loop.go to use new feature.

4. Update Documentation

  • Edit ARCHITECTURE.md if structural change
  • Edit README.md if user-facing
  • Add godoc comments

Release Process

Use the release-runbook skill:

bash
1~/.codex/skills/release-runbook/scripts/release.sh --version 1.2.3 --test-cmd "make test"

Code Style

  • Standard Go formatting (gofmt)
  • Conventional commits for commit messages
  • Add tests for new functionality
  • Update documentation

Resources

  • ARCHITECTURE.md - Full architecture documentation
  • README.md - User documentation
  • CONTRIBUTING.md - Contribution guidelines
  • AI_POLICY.md - AI contribution policy

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is looper-go-dev?

Ideal for Go-based AI Agents needing autonomous loop runner capabilities for streamlined development workflows. looper-go-dev is a Go-based skill for implementing autonomous AI loop runners, providing a structured approach to agent development and configuration.

How do I install looper-go-dev?

Run the command: npx killer-skills add nibzard/looper-go. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for looper-go-dev?

Key use cases include: Automating AI loop runner tasks for enhanced efficiency, Generating prompt templates for customized AI interactions, Debugging autonomous AI systems using internal logging facilities.

Which IDEs are compatible with looper-go-dev?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for looper-go-dev?

Requires Go programming language proficiency. Limited to autonomous AI loop runner workflows. Dependent on internal configuration and agent runner implementations.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add nibzard/looper-go. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use looper-go-dev immediately in the current project.

Related Skills

Looking for an alternative to looper-go-dev or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI