AU

An autonomous agent mode that performs iterative coding, testing, and debugging until a success condition is met.

Install

mkdir -p .claude/skills/autonomous-loop && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/4377" && unzip -o skill.zip -d .claude/skills/autonomous-loop && rm skill.zip

Installs to .claude/skills/autonomous-loop

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Iterate until success or limit, composing existing skills with Jidoka integration
81 charsno explicit “when” trigger
Advanced

Key capabilities

  • Execute recurring coding and linting cycles
  • Automate bug resolution tasks
  • Integrate with Jidoka escalation tiers
  • Perform success verification via qa-commit
  • Track progress with session-status

How it works

The skill iterates through a loop of implementation, review, and verification, using Jidoka tiers to decide whether to continue or escalate to human intervention.

Inputs & outputs

You give it
Task description or trigger phrase
You get back
Autonomous iteration report

When to use autonomous-loop

  • Run auto-fix loops for linting errors
  • Iteratively implement a feature until tests pass
  • Execute autonomous bug resolution tasks
  • Continuously attempt deployment-ready commits

About this skill

Autonomous Loop Skill (Ralph Wiggum)

Keep iterating until success without human intervention per attempt. Composes existing skills and respects Jidoka escalation.

When to Use

  • User requests hands-off iteration
  • Explicitly triggered with keywords

Trigger Phrases

  • "ralph mode"
  • "keep going"
  • "iterate until done"
  • "autonomous"
  • "don't stop"

Parameters

ParamDefaultDescription
max_iterations5Max attempts before pause
success_criteriatypecheck + lint + ReadLints cleanWhat defines success

Phase 1: Initialize

  1. Acknowledge activation
  2. Invoke session-status skill for current state
  3. Initialize counters:
    • iteration = 0
    • error_history = [] (shared with debug skill)

Output:

Entering autonomous loop. Max 5 iterations.
Current: [session-status header]

Phase 2: Execute Loop

FOR iteration IN 1..max_iterations:
    
    2.1: Execute current task action
         - Implement changes per commit plan
         - Run npm run typecheck
         - Run npm run lint
    
    2.2: Invoke pr-review skill
         - If BLOCK: proceed to 2.4
         - If PASS: proceed to 2.3
    
    2.3: Invoke qa-commit skill
         - If GREEN: proceed to 2.5
         - If RED: proceed to 2.4
    
    2.4: Invoke debug skill
         - Debug skill checks Jidoka tier internally
         - If Tier 2/3 escalation: EXIT loop, return JIDOKA
         - If Tier 1 fix attempted: CONTINUE loop
    
    2.5: Success checkpoint
         - Log iteration as SUCCESS
         - Proceed to next commit or EXIT if done

Phase 3: Iteration Report

After each iteration, output:

## Iteration [N]/[max]

| Step | Skill | Result |
|------|-------|--------|
| Execute | (implementation) | [files changed] |
| Review | pr-review | PASS/BLOCK |
| Verify | qa-commit | GREEN/RED |
| Debug | debug | [if invoked] |

**Outcome:** [SUCCESS / CONTINUE / JIDOKA / MAX]

Phase 4: Exit and Report

On loop exit, invoke session-status skill and output:

## Autonomous Loop Complete

**Exit reason:** [SUCCESS / JIDOKA / MAX / INTERRUPT]
**Iterations:** [N] of [max]

| Iter | Action | Result |
|------|--------|--------|
| 1 | [description] | [outcome] |
| 2 | [description] | [outcome] |

[session-status footer with next steps]

Exit Conditions

ConditionTriggerResult
SUCCESSAll checks pass, commit completeNormal exit, proceed to next commit
JIDOKATier 2/3 escalation triggeredExit loop, present options to human
MAXiteration >= max_iterationsExit loop, report and wait for guidance
INTERRUPTUser sends messageExit loop, respond to user

Safety Guardrails

  • NEVER auto-commit without GREEN from qa-commit
  • NEVER auto-push to remote
  • NEVER delete files without explicit approval
  • PAUSE on any destructive operation
  • EXIT on user message (treat as INTERRUPT)

Integration with Jidoka

Ralph Wiggum respects Jidoka escalation tiers:

TierRalph Behavior
Tier 1 (error_count < 3)Continue autonomously, debug skill handles
Tier 2 (same error 3x)EXIT loop, Jidoka presents options
Tier 3 (any error 5x)EXIT loop, Jidoka requires human triage

Integration

This skill composes:

  • session-status - Progress tracking
  • pr-review - Technical validation
  • qa-commit - QA contract verification
  • debug - Error fixing with Jidoka

This skill is invoked by:

  • User trigger phrases
  • agent.mdc when user requests autonomous mode

Invocation

Trigger with: "ralph mode", "keep going", "iterate until done"

Tools Used

ToolPurpose
Shellnpm run typecheck, npm run lint
ReadLintsIDE diagnostic errors
GrepPattern search in code
SemanticSearchFind implementations
ReadRead file contents
StrReplaceMake code changes
Browser MCPVisual verification (via qa-commit)

When not to use it

  • Destructive file operations without approval
  • Tasks requiring human-only judgment
  • Auto-pushing to remote repositories

Prerequisites

session-statuspr-reviewqa-commitdebug

Limitations

  • Limited to 5 iterations by default
  • Requires explicit approval for file deletion
  • Stops on Tier 2 or 3 Jidoka escalation

How it compares

This approach automates the entire feedback loop until a success condition is met, rather than requiring manual trigger for every step.

Compared to similar skills

autonomous-loop side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
autonomous-loop (this skill)27moNo flagsAdvanced
using-superpowers953moNo flagsBeginner
ultrawork112moNo flagsAdvanced
clawhub252moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

using-superpowers

obra

Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists

95205

ultrawork

Yeachan-Heo

Parallel execution engine for high-throughput task completion

11184

clawhub

openclaw

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.

25151

skill-installer

openai

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

29141

continuous-learning

affaan-m

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

995

memory-keeper-proactive-context-maintenance

b4CU-R4U

Automatically detect and maintain memory freshness by monitoring context staleness, significant code changes, task completions, and phase transitions. Proactively suggests and executes memory sync operations with user confirmation. Use when the user says "sync memory", "update context", or when the Skill detects that context is stale (>2 hours), significant changes have occurred (new commits), tasks completed, or major milestones reached. Replaces passive "context is stale" warnings with active maintenance.

694

Search skills

Search the agent skills registry