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.
curl -O https://raw.githubusercontent.com/psu-efd/pyHMT2D/main/.agents/skills/hmt-open/SKILL.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/skills/psu-efd/pyhmt2d/hmt-open)<a href="https://agentmods.dev/skills/psu-efd/pyhmt2d/hmt-open"><img src="https://agentmods.dev/badge/skills/psu-efd/pyhmt2d/hmt-open/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/psu-efd/pyhmt2d/hmt-open"><img src="https://agentmods.dev/badge/skills/psu-efd/pyhmt2d/hmt-open.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00056 | $0.00605 |
| Opus 5.5 | $0.00022 | $0.00242 |
| Sonnet 5.5 | $0.00011 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
hmt-open 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open a pyHMT2D hydraulic model project and display its contents.
Usage
/hmt-open [project_file]
The project file path is optional — if omitted, this skill scans the current directory.
Steps
-
Find the project file. If the user provided a path in the command, use it directly. Otherwise, scan the current directory:
hmt-cli list_model_files --args '{"directory": "."}'Show the found files as a table (file, model type, case name). If multiple files are found, ask the user which one to open. If none are found, tell the user no model files were detected and stop.
-
Open the project.
hmt-cli get_project_info --args '{"project_file": "<path>"}'On error: report the message and stop. On success: report model type, case name, number of cells, number of material zones, and number of boundary conditions.
-
Show materials.
hmt-cli get_materialsPresent as a Markdown table: ID | Name | Manning's n
-
Show boundary conditions. (run after step 3 completes — do NOT run in parallel)
hmt-cli get_boundary_conditionsPresent as a Markdown table: ID | Name | Type | Value | Units
-
Look for a result file. (run after step 4 completes — do NOT run in parallel) Check the same directory for
.h5,.hdf, or.hdf5files. If found, offer to inspect available variables:hmt-cli get_result_variables --args '{"result_file": "<result_file>"}'Report: variable names and number of time steps.
Important: Each
hmt-clicall spawns a separate process that opens its own HEC-RAS COM instance. Always run these calls sequentially to avoid simultaneous instances that can cause file I/O conflicts. -
Suggest next steps based on what was found:
- If result file present: "Run
/hmt-resultsto query simulation output." - If no result file: "Run
/hmt-runto execute the simulation." - To change parameters: "Run
/hmt-modify."
- If result file present: "Run
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.
- 2mo ago First seen · 63 lines · 56 tokens per session scan A 0a3eedbe598e
hmt-open is a skill published in the GitHub repository psu-efd/pyHMT2D (134 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 605 once invoked, about $0.0002 per session on Opus 5.5. 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.
hmt-open compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hmt-openpsu-efd/pyHMT2D | Skill | 134 | 2mo ago | MIT | A | 56 | Claude Code, Codex |
| academic-paper-reviewbytedance/deer-flow | Skill | 85k | yesterday | MIT | A | 95 | Claude Code, Codex |
| personal-genomicssammcj/agentic-coding | Skill | 168 | 2d ago | Apache-2.0 | A | 56 | Claude Code |
| huggingface-vision-trainermetaspartan/cybara | Skill | 34 | yesterday | MIT | A | 37 | Claude Code, Codex |
| huggingface-papersmetaspartan/cybara | Skill | 34 | yesterday | MIT | A | 30 | Claude Code, Codex |
| publish-the-run-that-did-not-workbrcampidelli/chimera-agent | Skill | 29 | yesterday | Apache-2.0 | A | 38 | Claude Code, Codex |
| suap-iff-apipedroiff0/awesome-skills | Skill | 1 | 14d ago | MIT | A | 102 | Claude Code, Codex |