🔁
AutomationTypeScript

Agent Loop

by jmagly

Agent Loop is an Automation skill for Claude Code, published by jmagly in aiwg.

209 stars32 forkson jmagly/aiwgAdded 2026/09/04+1% in starsRepository updated 2026/09/03
View source on GitHubDownload repo ZIP
agentic-codingai-frameworkanthropicautonomous-agentsclaude-codecodexcopilotcursordeveloper-toolsfine-tuningmulti-agentmulti-platformorchestrationprompt-engineeringsdlctraining-datawarpworkflow-automation
Install in seconds
Install Agent Loop
Copy Agent Loop into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/jmagly/aiwg/tree/main/agentic/code/addons/agent-loop/skills/ralph ~/.claude/skills/ralph

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/jmagly/aiwg.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
agentic/code/addons/agent-loop/skills/ralph/SKILL.md in jmagly/aiwg
Installs to
~/.claude/skills/ralph
Collection
One of 25 skills cataloged from this repository
Category
Automation — 1860 skills

What Agent Loop does

Agent Loop executes a task in repeated cycles until verifiable completion criteria are met. Use it when you want an agent to keep trying, learn from failures, and report the final status.

Agent Loop is cataloged under Automation on DirSkills. Agent Loop comes from a repository tagged agentic-coding, ai-framework, anthropic, autonomous-agents and claude-code.

Documentation

README

Agent Loop

You are the Agent Loop Orchestrator - executing iterative AI task loops until completion criteria are met.

Core Philosophy

"Iteration beats perfection" - errors become learning data within the loop rather than session-ending failures.

Your Role

You manage the iterative execution cycle:

  1. Parse task definition and completion criteria
  2. Execute the task
  3. Verify completion criteria
  4. Learn from failures and extract actionable insights
  5. Iterate if not complete (re-execute with learnings)
  6. Report final status with completion report

Natural Language Triggers

Users may say:

  • "ralph this: [task]"
  • "ralph [task]"
  • "loop until: [criteria]"
  • "keep trying until [condition]"
  • "iterate on [task] until [done]"
  • "agent loop [task]"

This is the opening of the README. Read the full README on GitHub.

Commands Agent Loop provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

  • /ralph-resume
  • /ralph-abort
  • /ralph

Frequently asked about Agent Loop

  • What else does jmagly publish alongside Agent Loop?

    Agent Loop is one of 25 skills that DirSkills catalogs from jmagly/aiwg, the repository it ships in. Its siblings there include Agent Loop, Agent Loop External and Agent Persistence. Each one is a separate skill with its own page in this directory, installs the same way Agent Loop does, and is maintained by jmagly in that same repository. The rest of the collection is listed on the jmagly/aiwg page.

  • How does Agent Loop compare to other Automation skills?

    Agent Loop ranks #1707 by stars among the 1860 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Agent Loop against them. Open each page to compare what they document and how they install.

More from jmagly/aiwg

Agent Loop is one of 25 skills cataloged on DirSkills from jmagly/aiwg.

See all 25 skills →
🔁
2h ago

Agent Loop

Agent Loop detects requests for iterative autonomous task execution and routes them to the right loop executor. Use it when a user wants to keep trying, fix until green, or run an explicit agent loop.
AI Engineering
20932
🔁
2h ago

Agent Loop External

Agent Loop External launches a long-running agent loop outside the current session with saved state. Use it for crash recovery, parallel runs, and CI/CD-backed tasks that need resumable execution.
AI Engineering
20932
🛡️
2h ago

Agent Persistence

Agent Persistence defines reusable human-in-the-loop gates for persistent agent loops. Use it when you need authorization for destructive actions, policy overrides, or recovery escalation.
AI Engineering
20932
🔄
2h ago

Al External

Al External launches long-running iterative loops outside the AI session with saved state. Use it for tasks that need crash recovery, parallel runs, or CI/CD integration.
AI Engineering
20932
🧠
2h ago

Al Memory

Al Memory lets you list, query, and clear semantic memory entries from loop iterations. Use it to review lessons learned, failure patterns, and success patterns across runs.
AI Engineering
20932
🧪
2h ago

Auto Test Execution

Auto Test Execution runs relevant tests after code-generating agents modify source files. It is used to enforce an execute-before-return workflow and retry when tests fail.
Quality
20932

More Automation skills

Agent Loop is one of 1860 Automation skills cataloged on DirSkills, ranked #1707 by stars among them.

Browse all Automation skills →
🔁
3w ago

Autonomous Loops

Autonomous Loops provides patterns and reference implementations for running Claude Code in autonomous loops, from simple sequential pipelines to RFC-driven multi-agent DAG systems. Retained for compatibility; use continuous-agent-loop for new guidance.
Automation
239.8K36.4K
🤖
3w ago

Autonomous Agent Harness

Autonomous Agent Harness turns Claude Code into a self-directing agent system with persistent memory, scheduled tasks, computer use, and task queuing. Use it when continuous autonomous operation, scheduled tasks, or self-directing agent loops are needed.
Automation
239.8K36.4K
🔍
3w ago

Automation Audit Ops

Automation Audit Ops audits live automations, jobs, hooks, and connectors to identify what is working, broken, redundant, or missing before any fixes are made.
Automation
239.8K36.4K