Skip to content
KitploitKITPLOIT
ToolsExploitsBlog
Log in
Submit
ToolsExploitsBlog
Submit

Hacking, PenTest, and Cybersecurity Tools for Your Security Arsenal!

Kitploit is a directory of hacking, cybersecurity, and pentesting tools. Discover the latest project updates to find vulnerabilities, analyze systems, automate testing, and strengthen your security.

FeedsContactPrivacy© 2026 Kitploit

Tool Directory

Categories

View all categories
Loading categories
ralph — Ralph Wiggum plugin implementation that works after the CVE-2025-54795 security patch | Kitploit
Tools/GitHubGitHub/alonisser/ralph
General Purpose UtilitiesScripting & AutomationUtilities & FrameworksLearning & Education
GitHubalonisser/ralph

ralph

Ralph Wiggum plugin implementation that works after the CVE-2025-54795 security patch

View Repository
13610 months agoNot yet reviewed
Share

Ralph

A working implementation of the Ralph Wiggum autonomous loop technique for Claude Code.

Background

The official ralph-wiggum plugin in Anthropic's plugin marketplace is currently broken due to a security update in Claude Code v1.0.20 (August 2025).

The security patch (CVE-2025-54795) correctly blocks $() command substitution and multi-line bash commands to prevent command injection attacks. However, the official plugin's command file contains multi-line bash that triggers this protection:

Error: Bash command permission check failed for pattern "...": 
Command contains newlines that could separate multiple commands

Multiple issues have been filed:

  • #12170 - Nov 23, 2025
  • #15640 - Dec 29, 2025
  • #15708 - Dec 29, 2025
  • #16037 - Jan 1, 2026

As of January 3, 2026, these remain unfixed.

This Plugin

This is a clean reimplementation that works with current Claude Code security restrictions.

Key architectural difference: The official plugin tries to execute bash directly from the command file. This plugin instead instructs Claude to create the state file using its Write tool, keeping the command file pure markdown with no bash execution. The stop hook runs as a separate shell script outside the permission system.

Installation

Option 1: Dev mode (for testing)

claude --plugin-dir /path/to/ralph

Option 2: Local marketplace (for permanent use)

# Create marketplace
mkdir -p ~/claude-plugins/.claude-plugin
echo '{"name": "local", "owner": {"name": "You"}}' > ~/claude-plugins/.claude-plugin/marketplace.json

# Move plugin into marketplace
mv /path/to/ralph ~/claude-plugins/

# In Claude Code:
/plugin marketplace add ~/claude-plugins
/plugin install ralph@local

Usage

/ralph:ralph-loop "Your task" --max-iterations 30 --completion-promise "DONE"

Arguments

ArgumentDescriptionDefault
promptThe task to complete(required)
--max-iterations NSafety limit30
--completion-promise TEXTCompletion signalTASK_COMPLETE

Examples

/ralph:ralph-loop "Build a REST API with tests" --completion-promise "API_COMPLETE"
/ralph:ralph-loop "Follow the instructions in CLAUDE.md" --max-iterations 50 --completion-promise "BENCHMARK_COMPLETE"

Cancel

/ralph:cancel-ralph

How It Works

  1. Command instructs Claude to create .claude/ralph-loop.local.md with task and config
  2. Claude works on the task
  3. Claude finishes its turn (natural stop)
  4. Stop hook fires, checks transcript for <promise>COMPLETION_PROMISE</promise>
  5. Not found? → Hook returns {"decision": "block", "reason": "..."}, Claude continues
  6. Found? → Hook allows stop, cleans up state file
  7. Max iterations? → Hook allows stop regardless

Requirements

  • Claude Code 1.0.20+
  • jq (for JSON parsing in stop hook)

Credits

  • Geoffrey Huntley — Original Ralph technique
  • Boris Cherny — Official plugin
  • Ralph — This working reimplementation

License

MIT

Download Tool

Most Popular

View all →

Discover the most used tools by our community.

  • 1

    OsintHunter

    letox4/osinthunter

    🎯 The ultimate OSINT toolkit: investigation graph, confidence scoring, alias families, map, timeline and reports. 49 modules, 400+ sites, no API keys required.

    851
  • 2

    ghostlock-app

    yukonga/ghostlock-app

    GhostLock One-Tap Execution App (CVE-2026-43499)

    538
  • 3

    ARTEX

    baarai/artex

    LLM multi-agent autonomous penetration testing platform with planner/worker agents, asset and exploration graphs, MITM traffic recording, and vulnerability retesting.

    420
  • 4

    redforge

    cybersecurity91/redforge

    Browser-side red team toolkit with 102 offline tools for recon, payload generation, credential attacks, crypto, encoding and engagement reporting.

    357
  • 5

    looking-glass

    anonghosty/looking-glass

    CSIRT platform that ingests Shadowserver reports into MongoDB and replays them as interactive maps, analysis, findings, advisories and executive dashboards.

    297
  • 6

    CyberStrikeAI

    ed1s0nz/cyberstrikeai

    The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

    280

Explore all tools

Browse our collection of tools

View all tools →