Move eval harness to submodule (#1541)

This commit is contained in:
Drew Ritter
2026-05-13 12:25:41 -07:00
committed by GitHub
parent 3d6dc90c6d
commit d25618db58
120 changed files with 11 additions and 12415 deletions

View File

@@ -96,7 +96,7 @@ Skills are not prose — they are code that shapes agent behavior. If you modify
## Eval harness
Skill-behavior evals live at `evals/` see `evals/README.md`. Drill (the harness) drives real tmux sessions of Claude Code / Codex / Gemini CLI and judges skill compliance with an LLM verifier. Plugin-infrastructure tests still live at `tests/`.
Skill-behavior evals live in the `evals/` submodule — after cloning, run `git submodule update --init evals`, then see `evals/README.md`. Drill (the harness) drives real tmux sessions of Claude Code / Codex / Gemini CLI and judges skill compliance with an LLM verifier. Plugin-infrastructure tests still live at `tests/`.
## Understand the Project Before Contributing