agent loops skills

8 tagged agent loops, measured the same way as everything else here.

opcore

01

the-open-engine/zeroshot

Skill Claude CodeCodex

Use for repository code intelligence and introduced-change validation in Zeroshot.

1.8k +6 yesterday A 17 tokens original MIT

looper

02

ksimback/looper

Skill Claude CodeCodex

Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council. Use when the user wants to design, build, or set up an agent loop, iterative agent workflow, self-review loop, LLM-as-judge loop, multi-model council, reviewer/judge gate, or /goal-style looping process. Start from a…

708 23d ago A 157 tokens original MIT

browser

03

nullskymc/Aurevoy

Skill Claude CodeCodex

A browser-automation skill that controls a web browser to load pages, interact with forms and buttons, inspect page structure, and capture screenshots.

10 26d ago A 63 tokens original MIT

research

04

nullskymc/Aurevoy

Skill Claude CodeCodex

A research skill for turning web searches into short reports or deeper, structured investigations. It can deliver the result in chat, Markdown, or HTML when a page-like layout is needed.

10 26d ago A 62 tokens original MIT

web-search

05

nullskymc/Aurevoy

Skill Claude CodeCodex

A web-search skill for finding current information, technical documentation, release notes, troubleshooting advice, and public code examples.

10 26d ago A 49 tokens original MIT

loop-architect

06

Frontier-Intelligence-Lab/loop-architect

Skill Claude CodeCodex

Design a safe, verifier-first loop for an AI coding agent — or refuse when a task should not be looped. Use when someone asks "can I automate this with an agent?" or wants to create, audit, or improve a loop for coding agents, scheduled agent work, autonomous repo maintenance, CI/QA loops, refactoring loops…

4 1mo ago A 167 tokens original MIT

thanos

07

thanospapage/thanos

Skill Claude CodeCodex

Turn any raw prompt into an optimized prompt with the right agent loop, skills, and model. Advisory only — never executes the task itself. TRIGGER when: user invokes /thanos followed by a raw prompt, or says "optimize this prompt", "what loop does this need", "improve my prompt", "how should I prompt for", "rewrite…

1 8d ago A 134 tokens original MIT