This Zenodo record is a frozen snapshot of ESFlow a module-grounded agentic AI framework for Earth system model (ESM) analysis, together with the sample data and full per-model benchmark outputs required to reproduce the results reported in the companion manuscript: Zhou, T., Qian, Y., and Leung, L. R.: Can We Trust LLMs for Complex Earth System Model Analysis? Silent Failure and Evidence from Module-Grounded Benchmarking, submitted to Geoscientific Model Development (GMD), 2026. ESFlow constrains the LLM to compose declarative YAML workflows from a validated tool catalog rather than generate analysis code from scratch. The deposit includes: Source code: the ESFlow framework, the 24-tool library for E3SM land-surface and hydrology analysis, the benchmark runner, the self-debug experiment runner, and the structural grading pipeline. Sample data: a representative subset of E3SM model output (land and river components) and GRDC streamflow observations sufficient to execute every reference workflow. Benchmark outputs: complete per-model results for all 336 single-shot runs and the iterative self-debug experiment, including LLM-generated YAMLs, Python scripts, raw responses, execution logs, and structural grading scores. Reproduction instructions are provided in the repository README.md. Disclaimer This material was prepared as an account of work sponsored by an agency of the United States Government. Neither the United States Government nor the United States Department of Energy, nor Battelle, nor any of their employees, nor any jurisdiction or organization that has cooperated in the development of these materials, makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness or any information, apparatus, product, software, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government or any agency thereof, or Battelle Memorial Institute. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof. PACIFIC NORTHWEST NATIONAL LABORATORY operated by BATTELLE for the UNITED STATES DEPARTMENT OF ENERGY under Contract DE-AC05-76RL01830