pyHMT2D: Skill for Claude Code

.agents/skills/hmt-results/SKILL.md

hmt-results is a skill for Claude Code, Codex from psu-efd/pyHMT2D. It costs 44 tokens per session (531 once invoked), scanned A, original, MIT.

A workflow for loading and examining results from flood or other hydraulic simulations. It can read result files and report values at points, statistics across the model area, flood extent, or cross-sections.

In plain words
What is it for?
Use it to query a variable at a location, calculate minimum and maximum values, measure flooded area above a depth threshold, or inspect a cross-section profile.
Why use it?
It provides a structured way to inspect simulation output without manually searching large result files.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is psu-efd/pyHMT2D's own configuration. It tells Claude Code and Codex how to work on pyHMT2D itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pyHMT2D configures →

Reuse

Borrowing it

Nothing to install: this file belongs to psu-efd/pyHMT2D. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/psu-efd/pyHMT2D/main/.agents/skills/hmt-results/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/psu-efd/pyHMT2D

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for hmt-results

README.md
[![agentmods](https://agentmods.dev/badge/skills/psu-efd/pyhmt2d/hmt-results.svg)](https://agentmods.dev/skills/psu-efd/pyhmt2d/hmt-results)
Your own site
<a href="https://agentmods.dev/skills/psu-efd/pyhmt2d/hmt-results"><img src="https://agentmods.dev/badge/skills/psu-efd/pyhmt2d/hmt-results.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 531 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.00531
Opus 5 $0.00022 $0.00266
Sonnet 5 $0.00009 $0.00106
Haiku 4.5 $0.00004 $0.00053

Measured 8d ago against content hash aff8e720674b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

hmt-results 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 8d 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.

.agents/skills/hmt-results/SKILL.md · 52 lines

What it actually says

Load simulation results and query values at points, domain-wide statistics, flood extent, or cross-section profiles.

Prerequisites

A project must be open. A result file (.h5 or .hdf) must exist.

Steps

  1. Find the result file. Check .hmt_session.json for result_file. If not set, inspect any .h5 / .hdf file:

    hmt-cli get_result_variables --args '{"result_file": "<path>"}'
    

    If multiple result files exist, ask the user which one to use.

  2. Load the results.

    hmt-cli read_results --args '{"result_file": "<path>", "timestep": -1}'
    

    Report: available variable names, number of time steps.

  3. Ask the user what they want to query. Offer these options:

    a) Value at a point — ask for x, y, variable name:

    hmt-cli get_value_at_point --args '{"x": <x>, "y": <y>, "variable": "<var>"}'
    

    b) Domain-wide statistics — ask for variable name:

    hmt-cli get_result_statistics --args '{"variable": "<var>"}'
    

    Report: min, max, mean, std, number of cells.

    c) Flood extent — ask for depth threshold (default 0.01 m):

    hmt-cli get_flood_extent --args '{"depth_threshold": <threshold>}'
    

    Report: flooded area in m² and km², percentage of domain flooded.

    d) Cross-section profile — ask for two (x,y) endpoints and variable:

    hmt-cli get_cross_section_profile --args '{"x1": <x1>, "y1": <y1>, "x2": <x2>, "y2": <y2>, "variable": "<var>", "n_points": 50}'
    

    Present as a table: Distance (m) | X | Y | Value.

  4. Offer further queries or suggest /hmt-export to create VTK files.

Changes

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.

  1. 8d ago First seen · 52 lines · 44 tokens per session scan A aff8e720674b

Subscribe to this mod's changes

hmt-results is a skill published in the GitHub repository psu-efd/pyHMT2D (131 stars, last pushed 29d ago), licensed MIT. It adds 44 tokens to every session and 531 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories