Skill Claude CodeCodex
Compare raw and official agent-tool surfaces using replicated AX tasks.
2 3d ago A 16 tokens
original Apache-2.0
A local-first toolkit for testing agent experience in Agent-Native developer tools.
Skill Claude CodeCodex
Compare raw and official agent-tool surfaces using replicated AX tasks.
Skill Claude CodeCodex
Turn replicated agent-experience findings into concise vendor reports.
Skill Claude CodeCodex
Capture agent runs with checkpoints, effect receipts, and redacted trajectories.
Skill Claude CodeCodex
Design controlled coding-agent tasks for measuring developer-tool agent experience.
Skill Claude CodeCodex
Build independent, deterministic verifiers for agent-tool tasks.