Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness compatibility checks, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior. Ships reusable CI templates that bring every check to any repository.
Python agent-evaluationagent-pluginsagent-securityagent-skillsagentic-aibenchmarkci-templatesclaude-codecodexevaluateevaluationharnesspluginplugin-evaluationsecurity-scannerskill-evalskill-evaluationskill-evaluatorskill-gap-analysisskills
#!/usr/bin/env python3
# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
"""Resolve the plugin install and the user's work tree in one place."""
import os
from pathlib import Path
MARKER = ".build-notes"
def plugin_root():
env = os.environ.get("CLAUDE_PLUGIN_ROOT")
if env and Path(env).is_dir():
return Path(env)
return Path(__file__).resolve().parent.parent
def project_root():
env = os.environ.get("CLAUDE_PROJECT_DIR")
if env and (Path(env) / MARKER).is_dir():
return Path(env)
return None
def stamp_origin(path=None):
"""Record where the notes cache lives so a copied install can find it."""
target = path or os.environ.get("BUILD_NOTES_CACHE") or str(Path("~/.cache/build-notes").expanduser())
dest = Path(plugin_root(), "notes-cache-origin")
dest.write_text(target + "\n", encoding="utf-8")
return dest