proofloop
01Plugin Claude Code
Plugin marketplace listing 1 plugin: proofloop.
Plugin Claude Code
Plugin marketplace listing 1 plugin: proofloop.
Plugin Claude Code
The first universal judge for Claude Code & Cowork. Auto-evaluates skill and agent execution quality with 7-dimension scoring, configurable rubrics, and dual-mode operation (auto hooks + manual /judge command).
Instructions file
Instructions for sattyamjjain/proofloop, covering claude.md, v4.3 scope contract (2026-05-03), build & development commands, architecture and data flow.
Agent
Read-only isolated agent that evaluates skill/agent execution quality.
Command
Side-by-side delta between two scorecards of the same skill.
Command
Compare skill scores against ideal benchmarks.
Command
Compare two Proofloop scorecards of the same skill with a narrative overlay.
Command
View and manage Proofloop auto-judge configuration.
Command
Evaluate the execution quality of a skill or agent.
Command
View score history and trends for skills.
Hook
Runs when the agent finishes a response, executing judge-on-stop.sh via bash. From sattyamjjain/proofloop.
Hook
Runs when a subagent finishes, executing judge-on-subagent-stop.sh via bash. From sattyamjjain/proofloop.
Hook
Runs on the StopFailure event, executing judge-on-stop-failure.sh via bash. From sattyamjjain/proofloop.
Skill Claude CodeCodex
Evaluates the execution quality of any skill or agent using 7-dimension scoring with configurable rubrics.