Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/psu-efd/pyhmt2d/claude-mdgit clone --depth 1 https://github.com/psu-efd/pyHMT2DWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/psu-efd/pyhmt2d/claude-md)<a href="https://agentmods.dev/instructions/psu-efd/pyhmt2d/claude-md"><img src="https://agentmods.dev/badge/instructions/psu-efd/pyhmt2d/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01462 | $0.01462 |
| Opus 5 | $0.00731 | $0.00731 |
| Sonnet 5 | $0.00292 | $0.00292 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade A, and why
pyHMT2D CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
91% identical to pyHMT2D AGENTS.md — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
# Install in editable mode (development)
pip install -e .
# Run all tests
pytest
# Run a specific test file
pytest tests/01_SRH_2D_Data/01_01_SRH_2D_Data_test.py
# Run tests with verbose output (already enabled via pytest.ini addopts = -s)
pytest -v
CLI tools (available after install):
# Convert HEC-RAS 2D mesh to SRH-2D format
hmt-cli ras_to_srh --args '{"ras_hdf_file": "input.hdf", "terrain_tif_file": "terrain.tif", "srh_case_name": "output"}'
# Convert SRH-2D results to VTK (last time step)
hmt-cli srh_to_vtk --args '{"srhhydro_file": "case.srhhydro", "output_file": "result.h5"}'
# Export SRH-2D mesh only to VTK
hmt-cli srh_to_vtk --args '{"srhhydro_file": "case.srhhydro", "output_file": "mesh.vtk", "mesh_only": true}'
Architecture
pyHMT2D automates and post-processes 2D hydraulic simulations for two external solvers: SRH-2D (USBR) and HEC-RAS 2D (USACE). It is Windows-only due to solver dependencies (SRH-2D via subprocess, HEC-RAS via COM interface).
Package Layout
pyHMT2D/
├── Hydraulic_Models_Data/ # Model-specific data and control
│ ├── Hydraulic_Models_Data_Base/ # Abstract base classes
│ │ ├── HydraulicModel.py # Base for all model controllers
│ │ └── HydraulicData.py # Base for all data readers
│ ├── SRH_2D/ # SRH-2D implementation
│ ├── RAS_2D/ # HEC-RAS 2D implementation
│ └── Backwater_1D/ # Simple 1D demo model
├── Calibration/ # Model calibration (scipy-based)
├── Parametric_Study/ # Batch/Monte Carlo parametric studies
├── Misc/ # Utilities shared across models
│ ├── Terrain.py # DEM/raster processing (rasterio)
│ ├── RAS_to_SRH_Converter.py # Mesh/BC format conversion
│ ├── vtk_utilities.py # VTK export and manipulation
│ └── tools.py # Result sampling and probing
└── __common__.py # Global config (verbose flag, etc.)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 116 lines · 1,462 tokens per session scan A 46160717e257
pyHMT2D CLAUDE.md is an instructions file published in the GitHub repository psu-efd/pyHMT2D (129 stars, last pushed 25d ago), licensed MIT. It adds 1,462 tokens to every session, about $0.0073 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to pyHMT2D AGENTS.md, differing in 8 lines, and is treated as a copy.
Other instructions, from other repositories
ag2 AGENTS.md
AGENTS.md instructions for ag2ai/ag2, covering ag2 development guidelines, ai-assisted contribution policy, architecture decision records (adr), code style guidelines and package structure.
PINA AGENTS.md
AGENTS.md instructions for PINA-org/PINA, covering pina — physics-informed neural architectures, quick reference, workflow: problem → model → solver → trainer, problem types and condition types.
FaST-LMM AGENTS.md
Instructions for fastlmm/FaST-LMM, covering coding notes for agents, general policies, cross-repository release coordination, numerical correctness and error handling.
AWETrim AGENTS.md
Instructions for awegroup/AWETrim, covering awetrim — agent context, what this repo is, module status, physics references and symbol ↔ code name table.
jax-numerics-agent AGENTS.md
Instructions for quattro/jax-numerics-agent, covering agents.md, scope, source of truth, agent workflow and global install note.
PINA CLAUDE.md
Claude Code instructions for PINA-org/PINA, a project described as: Physics-Informed Neural networks for Advanced modeling.