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 →
HERO — Anti-OverDefense 🧱 · · · · 🧱 You asked
| Stars | 439 |
| Forks | 10 |
| Language | Markdown |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 60.1525737108031/100 |
| Last Updated | 2026-09-09 |
| Created | 2026-08-11 |
| Platforms | claude-code, cli, codex, gemini |
| Est. Tokens | ~19k |
These tools work well together with HERO-Anti-OverDefense for enhanced workflows:
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.
A collection of AI agent skills for Clawdbot, Claude Code, Codex
103 ready-to-use AI agent skills for Claude Code, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, Windsurf,
Continuously sync your AI setups with one command. Codebase tailor suited agent skills, MCPs and config files
Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and p
Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, a
100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB backend and advanced
Explore other popular codex skill tools:
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.
HERO-Anti-OverDefense is primarily written in Markdown. It covers topics such as agents-md, ai-agents, antigravity.
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.
HERO-Anti-OverDefense is released under the MIT license, making it free to use and modify according to the license terms.
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.
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: