Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By severity1
Initialize a quality-gated task configuration by auto-discovering project tests, linters, Makefile targets, and CI checks, then enforce those gates during an autonomous development loop.
npx claudepluginhub severity1/severity1-marketplace --plugin this-little-wiggy"Mayor Quimby gives Ralph the instructions. Ralph executes them."
Type vibes, ship autonomy. Detects complex implementation tasks and wraps them in ralph-loop format with project-specific completion criteria.
You've already curated your workflows - slash commands, TDD prompts, issue references. Why write more prompts just to make them ralph-loop compatible?
this-little-wiggy lets you keep using your established workflows. Your existing prompts automatically get wrapped in ralph-loop format when they're complex enough to benefit from autonomous execution.
Intercepts complex implementation tasks and wraps them with project-specific completion criteria for autonomous execution.
Before: Manually structure every prompt with ralph-loop syntax and completion markers
After: Use your existing slash commands and prompts - this-little-wiggy handles the wrapping
# You type your natural prompt:
claude "build a REST API for todos"
# Or use slash commands with a prefix:
claude "Execute /tdd phase1"
# this-little-wiggy wraps it for ralph-loop:
/ralph-loop:ralph-loop --max-iterations 10 --completion-promise "COMPLETE" "build a REST API for todos
When complete:
- Tests pass
- Lint passes
- Build succeeds
Output <promise>COMPLETE</promise> when done."
Requirements:
pyyaml installed (pip install pyyaml)Windows users: Ensure Python is in your PATH and
pyyamlis installed in the Python environment that Claude Code uses.
1. Add the marketplace:
claude plugin marketplace add severity1/severity1-marketplace
2. Install the plugin:
claude plugin install this-little-wiggy@severity1-marketplace
3. Restart Claude Code
Verify installation with /plugin command. You should see the this-little-wiggy plugin listed.
1. Clone the repository:
git clone https://github.com/severity1/this-little-wiggy.git
cd this-little-wiggy
2. Add the local marketplace:
claude plugin marketplace add /absolute/path/to/this-little-wiggy/.dev-marketplace/.claude-plugin/marketplace.json
Replace /absolute/path/to/ with the actual path where you cloned the repository.
3. Install the plugin:
claude plugin install this-little-wiggy@local-dev
4. Restart Claude Code
Verify installation with /plugin command. You should see "1 plugin available, 1 already installed".
/this-little-wiggy:init
The wizard:
.claude/this-little-wiggy/config.ymlNormal prompts - complex tasks auto-detected:
claude "implement user authentication"
claude "build a REST API for todos"
Slash commands - prefix with a word to prevent premature expansion:
claude "Execute /tdd phase1"
claude "Implement /tdd GH issue 32"
Why the prefix? Without it, slash commands expand immediately before the hook can evaluate them. Adding "Execute", "Implement", or any word first lets the hook wrap the command with ralph-loop.
Bypass:
claude "* just fix this one line" # * prefix bypasses
claude "/ralph-loop:ralph-loop ..." # already wrapped
# .claude/this-little-wiggy/config.yml
defaultMaxIterations: 10
ralphWrapper: |
/ralph-loop:ralph-loop --max-iterations 10 --completion-promise "COMPLETE" "{task}
When complete:
- Tests pass
- Lint passes
- Build succeeds
Output <promise>COMPLETE</promise> when done."
User prompt → Hook (prompt-evaluator.py) → RALPH-LOOP DIRECTIVE → Claude executes /ralph-loop:ralph-loop
The hook reads your project config and wraps prompts with completion criteria. Claude then evaluates whether to execute the wrapped prompt based on task complexity.
uv run pytest tests/ -v
MIT
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Implementation of the Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.
Drive a goal to completion autonomously while enforcing backpressure (lint, tests, verification) at every step.
Autonomous coding using the Ralph Wiggum technique - simple loops, persistent memory, one task at a time
Self-referential development loop plugin - iteratively improves on tasks until completion
SDLC enforcement for AI agents — TDD, planning, self-review, CI shepherd
Reliability hooks for Claude Code - prevents common mistakes and enforces quality standards
Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability, user-decision questions, and plan-mode assessment
Automatically maintains CLAUDE.md files as codebases evolve using hooks, agents, and skills
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim