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.
git clone --depth 1 https://github.com/SteadfastAsArt/geoscience-skillsWrote 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/commands/steadfastasart/geoscience-skills/model-3d)<a href="https://agentmods.dev/commands/steadfastasart/geoscience-skills/model-3d"><img src="https://agentmods.dev/badge/commands/steadfastasart/geoscience-skills/model-3d.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 5.1 | $0.00014 | $0.00484 |
| Opus 5 | $0.00007 | $0.00242 |
| Sonnet 5 | $0.00003 | $0.00097 |
| Haiku 4.5 | $0.00001 | $0.00048 |
Grade A, and why
model-3d 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 7d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
3D Geological Modelling Workflow
Guide the user through building a 3D geological model. Determine the appropriate skill chain based on input data and modelling goals.
Decision Tree
-
What input data do you have?
- GIS layers (shapefiles, rasters, DEMs) → Use
gemgisskill for data preparation - Borehole data / orientations → Load directly into modelling engine
- Pre-processed surfaces → Skip to model setup
- GIS layers (shapefiles, rasters, DEMs) → Use
-
Which modelling engine fits your problem?
- Complex faulted geology, implicit surfaces, GPU support → Use
gempyskill - Fold-dominated structures, lightweight, tetrahedral meshes → Use
loopstructuralskill
- Complex faulted geology, implicit surfaces, GPU support → Use
-
Visualization needs?
- Interactive 3D model rendering → Use
pyvistaskill - Cross-sections and map views → matplotlib (built-in)
- Interactive 3D model rendering → Use
Skill Chain
gemgis (data prep from GIS) → gempy (implicit modelling, GPU) → pyvista (3D viz)
→ loopstructural (fold-focused, light) → pyvista (3D viz)
Step Prompts
For each step, invoke the relevant domain skill and follow its guidance.
Step 1: Data Preparation
- Extract surface points and orientations from GIS data
- Reproject coordinates to a consistent CRS
- Prepare topography and stratigraphic contact data
Step 2: Model Setup
- Define model extent and resolution
- Assign stratigraphic pile and fault network
- Set surface points and orientation gradients
Step 3: Compute Model
- GemPy: run interpolation with dual kriging, configure GPU if available
- LoopStructural: build model with fold constraints, set solver options
- Check for geological consistency (layer ordering, fault offsets)
Step 4: Validate
- Compare model surfaces against input data
- Check cross-sections for geological plausibility
- Evaluate model uncertainty if supported
Step 5: Visualization
- Render 3D block model and surfaces interactively
- Extract cross-sections at key locations
- Export model to common formats (VTK, GOCAD)
$ARGUMENTS
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.
- 7d ago First seen · 61 lines · 14 tokens per session scan A af2eafc5a8ae
model-3d is a command published in the GitHub repository SteadfastAsArt/geoscience-skills (57 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 484 once invoked, about $0.0001 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.
Other commands, from other repositories
diff
Quantitative volume comparison between a CadQuery model and a reference STEP file.
graphite-morphology-classify
Classify graphite in a cast-iron micrograph per ASTM A247 / ISO 945-1, quantify nodularity, and read the matrix — the single most diagnostic observation in a cast-iron case.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.