by gaasher · Codex Skill · ★ 114
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 | 114 |
| Forks | 13 |
| 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 |
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 114 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 114 stars and 13 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.