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/cxcscmu/skilllearnbench/glm-simulationnpx skills add cxcscmu/SkillLearnBench --skill glm-simulationgit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWhat 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 | $0.00019 | $0.00875 |
| Opus 5 | $0.00010 | $0.00438 |
| Sonnet 5 | $0.00004 | $0.00175 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade A, and why
glm-simulation 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 2d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GLM Simulation Skill
Overview
The General Lake Model (GLM) is a 1-D hydrodynamic lake model that simulates vertical water temperature and mixing. It reads configuration from a Fortran namelist file (.nml) and produces NetCDF output.
Installation & Setup
Prerequisites
- GLM executable must be available in your PATH or current directory
- Configuration file in Fortran namelist format (
.nml) - Forcing data (meteorology, inflows, outflows) as CSV files
Configuration File Structure
The GLM configuration file contains multiple namelist sections:
&glm_setup
sim_name = 'Lake Name'
max_layers = 500
min_layer_vol = 0.025
min_layer_thick = 0.10
max_layer_thick = 0.50
/
&light
Kw = 0.3 ! Light extinction coefficient [0.1-0.5]
/
&mixing
coef_mix_hyp = 0.5 ! Hypolimnetic mixing coefficient [0.3-0.7]
/
&meteorology
wind_factor = 1.0 ! Wind speed scaling [0.7-1.3]
lw_factor = 1.0 ! Longwave radiation scaling [0.7-1.3]
ch = 0.0013 ! Heat transfer coefficient [0.0005-0.002]
/
&time
start = '2009-01-01 12:00:00'
stop = '2015-12-30 12:00:00'
dt = 3600
/
&init_profiles
the_depths = 0, 1, 2, ...
the_temps = 5.1, 5.1, 5.1, ...
/
Running GLM
Basic Command
glm -f glm3.nml
The model reads the configuration and produces output (typically NetCDF) to the directory specified in &output.
Key Parameters for Calibration
These 5 parameters can be modified within specified ranges:
- Kw (light extinction): [0.1, 0.5] - affects light penetration
- coef_mix_hyp (hypolimnetic mixing): [0.3, 0.7] - affects deep water mixing
- wind_factor: [0.7, 1.3] - scales wind speed forcing
- lw_factor: [0.7, 1.3] - scales longwave radiation
- ch (heat exchange): [0.0005, 0.002] - affects surface heat transfer
Modifying Parameters
To modify a parameter in the .nml file:
import re
def update_nml_parameter(nml_file, section, param, value):
"""Update a parameter in a Fortran namelist file"""
with open(nml_file, 'r') as f:
content = f.read()
# Find the section and update the parameter
pattern = r'(&' + section + r'.*?)(\s+' + param + r'\s*=\s*)([^,\n]+)'
replacement = r'\g<1>\g<2>' + str(value)
content = re.sub(pattern, replacement, content, flags=re.DOTALL)
with open(nml_file, 'w') as f:
f.write(content)
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.
- 2d ago First seen · 102 lines · 19 tokens per session scan A 56deef401a38
glm-simulation is a skill published in the GitHub repository cxcscmu/SkillLearnBench (82 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 875 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 skills, from other repositories
rdkit
Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom…
pubchem-database
Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics.
Multimodal Fusion for Speaker Diarization
Combine visual features (face detection, lip movement analysis) with audio features to improve speaker diarization accuracy in video files. Use OpenCV for face detection and lip movement tracking, then fuse visual cues with audio-based speaker embeddings. Essential when processing video files with multiple visible…
routing-subtour-elimination
Subtour-elimination methods for TSP, VRP, pickup/dropoff routing, and routing MIPs with binary arc variables. Use when route-continuity constraints may permit disconnected cycles and the model needs MTZ constraints, flow-based connectivity constraints, DFJ subset cuts, or lazy/iterative subtour cuts.
scip-opt
SCIP optimization with PySCIPOpt. Use when facing an optimization problem with an objective, hard constraints, soft penalties, integer decisions, routing, assignment, scheduling, allocation, packing, capacity, inventory, or service-level rules. Prefer modeling and solving the problem with PySCIPOpt when it is…
Voice Activity Detection (VAD)
Detect speech segments in audio using VAD tools like Silero VAD, SpeechBrain VAD, or WebRTC VAD. Use when preprocessing audio for speaker diarization, filtering silence, or segmenting audio into speech chunks. Choose Silero VAD for short segments, SpeechBrain VAD for general purpose, or WebRTC VAD for lightweight…