loop-agent

Execute iterative development loops with checkpointing, cost tracking, and safety guardrails.

Updated Aug 23, 2026

Search Tags:#safety #iteration #checkpoint #autonomy #progress #cost #loop

One-click install

npx skills add https://github.com/nbarthelemy/claudenv --skill loop-agent-nbarthelemy

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: loop-agent
Source: https://github.com/nbarthelemy/claudenv/tree/main/.claude/skills/loop-agent
Command: npx skills add https://github.com/nbarthelemy/claudenv --skill loop-agent-nbarthelemy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Autonomous iterative development loop system. Repeatedly executes prompts until completion conditions are met, with checkpointing, cost tracking, and safety guardrails.

Core Features & Use Cases

Multiple Loop Modes: Standard, TDD, verification, and refinement loops.
Checkpointing & History: Save progress at milestones for auditability.
Safety Guardrails: Enforce max iterations, max time, and cost limits.
Use Case: Run a TDD loop for feature development until all tests pass.

Quick Start

Start a loop: /loop "Build a REST API with tests" --until "All tests passing"