Test that your Claude Code skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, activation checks, A/B experiments, CI gates.
Agent
Run Google Antigravity (Gemini) as the agent under evaluation in Coder Eval — installation, authentication, model and skill configuration, and how its telemetry maps to sandboxed, weighted scoring.
Agent
Configure and run the default Claude Code agent in Coder Eval — the full agent-config surface, direct vs. Bedrock authentication, permission modes, sandbox isolation, skills/plugins, early stop, and token telemetry.
Agent
Run OpenAI Codex as the agent under evaluation in Coder Eval — installation, authentication, task configuration, and how Codex telemetry maps to sandboxed, weighted scoring.
Agent
One task file, run on any harness, must be the same task. runlimits.maxturns was the field that broke that promise hardest: Claude Code enforced it, and Codex and Antigravity accepted it and never read it, so maxturns: 6 ran capped on one backend and unbounded on the other two.
Agent
Run OpenCode, the open-source terminal coding agent, as the agent under evaluation in Coder Eval — installation, provider authentication, model selection, and how its event stream maps to sandboxed, weighted scoring.