Mr Overkill

C+ 73 completed
Cli Tool
unknown / shell · tiny
32
Files
3,644
LOC
0
Frameworks
2
Languages

Pipeline State

completed
Run ID
#361961
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Skipped
Decision
skip_scaffold_dup
Novelty
27.48
Framework unique
Isolation
Last stage change
2026-04-16 18:15:42
Deduplication group #47868
Member of a group with 1 similar repo(s) — canonical #73051 view group →
Top concepts (2)
Project DescriptionLibrary
Repobility — same analyzer, your code, free for public repos · /scan/

AI Prompt

Create an automated code refactoring tool inspired by "Mr. Overkill." I need a system that forces two AI agents, one simulating Codex and another simulating Claude, into a continuous loop to refactor my code until it's excessively over-engineered. The tool should be runnable via shell scripts, requiring prerequisites like Node.js, jq, and perl. Include functionality to run a review loop to fix diffs against a target branch, and another script to suggest refactoring opportunities across the entire codebase. The core logic should manage the interaction between these agents.
shell scripting ai-tool refactoring automation codex claude cli
Generated by gemma4:latest

Catalog Information

Mr. Overkill is an automated loop that forces Codex and Claude into a locked room, continuously refactoring your code until it's 'perfectly over-engineered' or your API credit runs out.

Description

This tool is designed to burn tokens by ignoring 'good enough' and striving for 'unnecessarily complex.' It drains wallets by requiring OpenAI (Paid) AND Anthropic (Pro/Max) simultaneously. The loop might turn your 'Hello World' into a Microservices Architecture.

الوصف

هذا الأداة مصممة لحرق التokens من خلال تجاهل 'كاف' و стремها إلى 'مبالغ فيها بشكل غير ضروري.' يزيل الميزانية من خلال الحاجة إلى OpenAI (مدفوع) و Anthropic (Pro/Max) بشكل متزامن. قد يتسبب هذا الدورة في تحويل 'Hello World' إلى أرشيتكترا ميكروسيرفس.

Novelty

1/10

Tags

code-refactoring over-engineering api-credit-drain openai anthropic

Claude Models

claude-opus-4.6

Quality Score

C+
72.6/100
Structure
67
Code Quality
75
Documentation
55
Testing
70
Practices
78
Security
100
Dependencies
50

Strengths

  • Good test coverage (100% test-to-source ratio)
  • Good security practices \u2014 no major issues detected
  • Properly licensed project

Weaknesses

  • No CI/CD configuration \u2014 manual testing and deployment

Recommendations

  • Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
  • Add a linter configuration to enforce code style consistency

Security & Health

4.1h
Tech Debt (C)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (3)
Open data scored by Repobility · https://repobility.com
MIT
License
0.0%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

shell
69.1%
markdown
30.9%

Frameworks

None detected

Concepts (2)

All metrics by Repobility · https://repobility.com
CategoryNameDescriptionConfidence
Methodology: Repobility · https://repobility.com/research/state-of-ai-code-2026/
auto_descriptionProject Description> "Refactoring is not a task. It's a lifestyle."80%
auto_categoryLibrarylibrary70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/86119.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV