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 gaasher · Codex Skill · ★ 150
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Agent-Loop-Skills safe to install? View the security audit →
agent-loop-skills Loop until it's better — drop-in agentic loops, packaged as open-standard Agent Skills. Autoresearch · scientific writing · data analysis · code/SQL/prompt optimization · red-teaming — each a generic, reusable loop you bind to your own task at invocation time, that iterates against a real signal until the work is actually better. A real run. The tournament-autoresearch loop on a CIFAR-10 model under a fixed 5-epoch budget — competing agents propose a change each step, a self-calibrating judge keeps the winners (green) and discards the regre
| Stars | 150 |
| Forks | 19 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 66.5430383989818/100 |
| Open Issues | 1 |
| Last Updated | 2026-06-30 |
| Created | 2026-06-15 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~18k |
Looking for a Agent-Loop-Skills alternative? If you're comparing Agent-Loop-Skills 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.
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
239 evaluated academic Claude/agent skills across 17 research domains (bioinformatics, data science, clinical,
The skill layer for AI agents: npm for AI Agent Skills.
200+ production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture.
Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca
The Ultimate Claude Code Toolkit — 127 skills, 86 agents, 109 marketplace repos (11,700+ community skills), 30
Explore other popular codex skill tools:
Agent-Loop-Skills is Loop until it's better — drop-in agentic loops (autoresearch, scientific writing, data analysis, code/SQL/prompt optimization, red-teaming) as open-standard Agent Skills. Verification-gated; native on. It is categorized as a Codex Skill with 150 GitHub stars.
Agent-Loop-Skills is primarily written in Python. It covers topics such as agent-skills, agentic-loops, agentic-workflows.
You can find installation instructions and usage details in the Agent-Loop-Skills GitHub repository at github.com/gaasher/Agent-Loop-Skills. The project has 150 stars and 19 forks, indicating an active community.
Agent-Loop-Skills is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to Agent-Loop-Skills on Agent Skills Hub include claudepro-directory, AlterLab-Academic-Skills, openagentskill. 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: