is-gpt-nerfed — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by kiyoakii · Codex Skill · ★ 131

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is is-gpt-nerfed safe to install? View the security audit →

About is-gpt-nerfed

English · 简体中文 You pick a model in Codex. This tells you whether that model is actually the one answering. If it isn't, you get this: 🎉 Congrats! You've been nerfed! You asked for gpt-6-astra; the fingerprint says gpt-5.6-luna (91%). Enjoy the discount you didn't ask for. Example output, not a real verdict. The panel, and a session opened in place. Sample data, not real sessions. All clear · Suspicious · Nerfed What it checks Everything runs on your Mac. Nothing is uploaded. Codex records, for every turn, which model and reasoning effort it asked for. The plugin reads those records after each turn and flags what changed without you changing it: a model swap, a lower reasoning effort, a hidden internal model such

codexdegradationgptllmnerfopenai

Quick Facts

Stars131
Forks4
LanguagePython
CategoryCodex Skill
LicenseMIT
Quality Score65.8091536228756/100
Last Updated2026-09-18
Created2026-09-15
Platformscodex, python
Est. Tokens~15k

Compatible Skills

These tools work well together with is-gpt-nerfed for enhanced workflows:

  • open-responses-server — semantic(0.33)+complementary+same_lang+similar_pop+shared_platform (61%)
  • codex-hygiene — semantic(0.31)+complementary+same_lang+similar_pop+shared_platform (61%)
  • claude-code-gpt-5-codex — semantic(0.31)+complementary+same_lang+similar_pop+shared_platform (61%)

is-gpt-nerfed alternative? Top 6 similar tools

Looking for a is-gpt-nerfed alternative? If you're comparing is-gpt-nerfed with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • Overture by SixHq · ⭐ 630

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • repopack-py by abinthomasonline · ⭐ 121

    Python version of 📦 repopack (https://github.com/yamadashy/repopack) by yamadashy (https://github.com/yamadas

  • ai-microcore by Nayjest · ⭐ 108

    A handy lib for smooth interaction with large language models (LLMs) and crafting AI apps.

  • the-great-gpt-firewall by samber · ⭐ 100

    🤖 A curated list of websites that restrict access to AI Agents, AI crawlers and GPTs

  • ha-claude by Bobsilvio · ⭐ 81

    Home Assistant add-on: Claude Code, OpenAI/GPT, Gemini

  • GPT-CodeApp by blazickjp · ⭐ 52

    This project is everything Chat-GPT should be for developers! An advanced AI-driven coding companion tailored

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is is-gpt-nerfed?

is-gpt-nerfed is Shrinkflation detector for Codex. It is categorized as a Codex Skill with 131 GitHub stars.

What programming language is is-gpt-nerfed written in?

is-gpt-nerfed is primarily written in Python. It covers topics such as codex, degradation, gpt.

How do I install or use is-gpt-nerfed?

You can find installation instructions and usage details in the is-gpt-nerfed GitHub repository at github.com/kiyoakii/is-gpt-nerfed. The project has 131 stars and 4 forks, indicating an active community.

What license does is-gpt-nerfed use?

is-gpt-nerfed is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to is-gpt-nerfed?

The top alternatives to is-gpt-nerfed on Agent Skills Hub include Overture, repopack-py, ai-microcore. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools