Agent-One-Lab/AgentFly

Scalable and extensible reinforcement learning for LM agents.

122Stars on the repository
4Mods indexed here, across every type
2d agoLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

add-numbers

01

Agent-One-Lab/AgentFly

Skill Claude CodeCodex

Adds two integers using a bundled calculator script. Use whenever the user asks to add two numbers, compute a sum, or do "X plus Y". Always use the script — do not compute the sum yourself.

not rated 122 2d ago A 46 tokens original Apache-2.0

country-capital

02

Agent-One-Lab/AgentFly

Skill Claude CodeCodex

Looks up the capital city of a country from a bundled reference table. Use whenever the user asks "what is the capital of ". Always consult the reference; do not answer from memory.

not rated 122 2d ago A 43 tokens original Apache-2.0

hello-skill

03

Agent-One-Lab/AgentFly

Skill Claude CodeCodex

Replies to the user with a special greeting in the form "Hello from skill! ". Use this whenever the user says hello, hi, or greets you.

not rated 122 2d ago A 39 tokens original Apache-2.0

word-count

04

Agent-One-Lab/AgentFly

Skill Claude CodeCodex

Counts words in a piece of text using a bundled script. Use whenever the user asks how many words are in some text. Refuses empty input.

not rated 122 2d ago A 33 tokens original Apache-2.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: