agents tested by Argusic Runner

What the test found

All 6 harnesses generate with 0 errors (codex: 908 files, copilot: 687, cursor: 97, opencode: 733, antigravity: 824, pi: 732), lint/validate/garden pass cleanly, 661/661 tests pass, Codex CLI plugin marketplace installs and discovers all 92 plugins, plugin-eval framework evaluates skills end-to-end. One pre-existing environment gap: npx skills smoke test cannot run because container Node.js v18 is below the >=22.20.0 requirement.

Argusic installed agents in 25 minutes and launched it; verification reached Verified running for real. 4 of 5 recorded errors were worked through (see the timeline below).

Runsall runs of agents

This summary is drawn from the agent's recorded report for this run. Every figure traces to the log and recording above; nothing here is authored.