HERO-Anti-OverDefense — security grade SAFE, quality 60/100

Security audit verdict: SAFE · quality 60/100

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 wanshuiyin · Codex Skill · ★ 439

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

🔒 Is HERO-Anti-OverDefense safe to install? View the security audit →

About HERO-Anti-OverDefense

HERO — Anti-OverDefense 🧱 · · · · 🧱 You asked

agents-mdai-agentsantigravityclaude-codeclaude-mdcodexcoding-agentcursorgemini-cligithub-copilot

Quick Facts

Stars439
Forks10
LanguageMarkdown
CategoryCodex Skill
LicenseMIT
Quality Score60.1525737108031/100
Last Updated2026-09-09
Created2026-08-11
Platformsclaude-code, cli, codex, gemini
Est. Tokens~19k

Compatible Skills

These tools work well together with HERO-Anti-OverDefense for enhanced workflows:

  • agentrules-architect — semantic(0.46)+complementary+similar_pop+shared_platform (56%)
  • mda — semantic(0.24)+complementary+rare_topics+similar_pop+shared_platform (53%)

HERO-Anti-OverDefense alternative? Top 6 similar tools

Looking for a HERO-Anti-OverDefense alternative? If you're comparing HERO-Anti-OverDefense 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.

  • agent-skills by jdrhyne · ⭐ 241

    A collection of AI agent skills for Clawdbot, Claude Code, Codex

  • awesome-ai-agent-skills by seb1n · ⭐ 149

    103 ready-to-use AI agent skills for Claude Code, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, Windsurf,

  • ai-setup by caliber-ai-org · ⭐ 1.3k

    Continuously sync your AI setups with one command. Codebase tailor suited agent skills, MCPs and config files

  • quint-code by m0n0x41d · ⭐ 1.3k

    Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and p

  • SWE-AF by Agent-Field · ⭐ 993

    Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, a

  • codegraph-rust by Jakedismo · ⭐ 861

    100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB backend and advanced

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Markdown Agent Tools

Frequently Asked Questions

What is HERO-Anti-OverDefense?

HERO-Anti-OverDefense is HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code, Codex, Antigravity, Cursor, Copilot, Wind. It is categorized as a Codex Skill with 439 GitHub stars.

What programming language is HERO-Anti-OverDefense written in?

HERO-Anti-OverDefense is primarily written in Markdown. It covers topics such as agents-md, ai-agents, antigravity.

How do I install or use HERO-Anti-OverDefense?

You can find installation instructions and usage details in the HERO-Anti-OverDefense GitHub repository at github.com/wanshuiyin/HERO-Anti-OverDefense. The project has 439 stars and 10 forks, indicating an active community.

What license does HERO-Anti-OverDefense use?

HERO-Anti-OverDefense is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to HERO-Anti-OverDefense?

The top alternatives to HERO-Anti-OverDefense on Agent Skills Hub include agent-skills, awesome-ai-agent-skills, ai-setup. 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