Agent Loop Skills
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 Claude Code, portable across Codex, Cursor & other Skills hosts.
Agent Loop Skills is an open-source agent skill by gaasher, written mainly in Python, with 178 GitHub stars and the MIT license. Its code was last updated Jun 30, 2026.
Scan summary: scanned Nov 5, 2026 at commit f1169e6. No capabilities flagged by our checks. Scan policy
f1169e6 · Nov 5, 2026Findings (2)
- mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.Install or build failed in a clean environmentude` or `exclude`) 2. use a `src-layout` 3. explicitly set `py_modules` or `packages` with a list of names To find more information, look for "package discovery" on setuptools docs. hint: Build failures usually indicate a problem with the package or the build environment
- lowLow. Minor, or common in normal tools. Shown for information.No manifest declaring network access and environment variables (agent.json)
Network activity
Automated result for the commit shown. See our scan policy. View the scan log
Maintainers can claim the listing to rescan, or dispute a result.
Agent Loop Skills alternatives
View more →Similar agent skills in Research & Analysis, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.
| Name | Stars | Licence | Last updated | Scan |
|---|---|---|---|---|
| Agent Loop Skills (this page) gaasher | 178 | MIT | Jun 30, 2026 | Scanned, no flagged issues |
| RuView ruvnet | 102k | MIT | Nov 1, 2026 | Scanned, no flagged issues |
| AI Research SKILLs Orchestra-Research | 14k | MIT | Oct 11, 2026 | Scanned, no flagged issues |
| Auto Empirical Research Skills brycewang-stanford | 4.9k | None found | Oct 30, 2026 | Not scanned yet |
| Council Of High Intelligence 0xNyk | 4.7k | MIT | Oct 26, 2026 | Scanned, no flagged issues |
| Serenity Skill muxuuu | 4.1k | MIT | Oct 11, 2026 | Scanned, no flagged issues |