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 skills/steadfastasart/geoscience-skills/devitonpx skills add SteadfastAsArt/geoscience-skills --skill devitogit 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/skills/steadfastasart/geoscience-skills/devito)<a href="https://agentmods.dev/skills/steadfastasart/geoscience-skills/devito"><img src="https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/devito.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 | $0.00119 | $0.01584 |
| Opus 5 | $0.00060 | $0.00792 |
| Sonnet 5 | $0.00024 | $0.00317 |
| Haiku 4.5 | $0.00012 | $0.00158 |
Grade A, and why
devito 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.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devito - Symbolic PDE Solver
Quick Reference
from devito import Grid, Function, TimeFunction, Eq, solve, Operator
# Create grid
grid = Grid(shape=(101, 101), extent=(1000., 1000.))
# Velocity model
v = Function(name='v', grid=grid, space_order=4)
v.data[:] = 1500.
# Wavefield
p = TimeFunction(name='p', grid=grid, time_order=2, space_order=4)
# Wave equation: d2p/dt2 = v^2 * laplacian(p)
stencil = Eq(p.forward, solve(p.dt2 - v**2 * p.laplace, p.forward))
# Compile and run
op = Operator([stencil])
op(time_M=100, dt=0.5)
Key Classes
| Class | Purpose |
|---|---|
Grid |
Computational domain definition |
Function |
Spatial field on grid |
TimeFunction |
Time-dependent field |
SparseTimeFunction |
Point sources/receivers |
Operator |
Compiled computation kernel |
Essential Operations
Grid and Fields
from devito import Grid, Function, TimeFunction
# 2D/3D Grid
grid = Grid(shape=(nx, nz), extent=(x_size, z_size))
# Velocity model (spatial field)
v = Function(name='v', grid=grid, space_order=4)
v.data[:] = 1500.
# Wavefield (time-dependent)
p = TimeFunction(name='p', grid=grid, time_order=2, space_order=4)
Source and Receivers
from examples.seismic import RickerSource, Receiver, TimeAxis
time_range = TimeAxis(start=0., stop=1000., step=dt)
# Source
src = RickerSource(name='src', grid=grid, f0=10., npoint=1, time_range=time_range)
src.coordinates.data[0, :] = [500., 20.]
# Receivers
rec = Receiver(name='rec', grid=grid, npoint=101, time_range=time_range)
rec.coordinates.data[:, 0] = np.linspace(0., 1000., 101)
rec.coordinates.data[:, 1] = 20.
Build and Run
# Wave equation
stencil = Eq(p.forward, solve(p.dt2 - v**2 * p.laplace, p.forward))
src_term = src.inject(field=p.forward, expr=src * dt**2 * v**2)
rec_term = rec.interpolate(expr=p)
# Compile and execute
op = Operator([stencil] + src_term + rec_term)
op(time_M=nt-1, dt=dt)
# Results
shot_record = rec.data # (nt, nrec)
snapshot = p.data[0] # Current wavefield
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 172 lines · 119 tokens per session scan A 83b027495e54
devito is a skill published in the GitHub repository SteadfastAsArt/geoscience-skills (56 stars, last pushed 5mo ago), licensed MIT. It adds 119 tokens to every session and 1,584 once invoked, about $0.0006 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 skills, from other repositories
fix-ci
Fix CI failures and performance regressions for a Julia package PR by iterating - triage the latest CI results, fix one root cause, verify locally, push. Use when a PR's GitHub Actions or Buildkite CI is failing, or when CI jobs run slower than they do on the main branch. Verifies CPU and GPU compilation locally…
glm-lake-mendota
Simulate vertical water temperature profiles for lakes using the General Lake Model (GLM), calibrate key parameters to minimize RMSE against field observations, and produce validated NetCDF output.
map-to-evo-schemas
Use when implementing the reader and geoscience-object builder for an Evo data converter — turning a parsed file into evo-schemas objects. Covers implementing read file, building Pointset/TriangleMesh/grid/etc. objects, uploading arrays via dataclient.savetable or the parquet-hash pattern, and setting CRS, bounding…
scaffold-converter
Use when creating the package skeleton for a new Evo data converter with the create-converter CLI. Runs the scaffolding generator, chooses the converter type and import/export mode, installs the package, and verifies it was registered. Use for: 'scaffold a converter', 'set up a new converter package', 'run…
test-converter
Use when writing and running tests for an Evo data converter, and validating it with linting and type checks. Replaces the generated placeholder tests with real ones using sample data, then runs uv run test- , ruff, and mypy until green. Use for: 'test the converter', 'write converter tests', 'the converter tests…
build-evo-converter
Use when building a complete new Evo data converter from scratch, end to end. Orchestrates the four phases — scaffolding, discovery, mapping to Evo geoscience objects, and testing — for turning a third-party geoscience file format into published Evo objects. Use for: 'build a converter for X', 'add support for a new…