jfrog/agent-belt

Reproducible evaluation for AI coding agents. Multi-turn scenarios against Claude Code, Codex, Copilot, Cursor, Gemini CLI, Goose, OpenCode, or any custom agent you plug in; verify behavior with rule checks, workspace diffs, multi-judge LLM consensus; pin reliability with pass^k variance across trials. Git worktrees, optional Docker sandbox.

18Stars on the repository

14Mods indexed here, across every type

1mo agoLast push, which is what freshness is scored on

Apache-2.0Licence, which decides whether bodies are shown

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 2 mods

folio-ops

01

jfrog/agent-belt

Plugin Claude Code

Folio operations pack: bundles a plugin command (lookup) and a plugin skill (inventory-audit), both reaching the workspace's Folio MCP server.

18 1mo ago A tokens not measured original Apache-2.0

orders-pack

02

jfrog/agent-belt

Plugin Claude Code

Bundles a slash command (report-orders) and a skill (processing-watch) that both reach the workspace's ordersdb MCP server.

18 1mo ago A tokens not measured original Apache-2.0