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 skills add cxcscmu/SkillLearnBench --skill glm-calibrationgit clone --depth 1 https://github.com/cxcscmu/SkillLearnBenchWrote 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/cxcscmu/skilllearnbench/glm-calibration)<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/glm-calibration"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/glm-calibration.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 | $0.00020 | $0.00340 |
| Opus 5 | $0.00010 | $0.00170 |
| Sonnet 5 | $0.00004 | $0.00068 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
glm-calibration 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 3d 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.
What it actually says
GLM Calibration for Lake Temperature
Key Calibration Parameters (Lake Mendota)
| Parameter | Range | Effect |
|---|---|---|
Kw |
[0.1, 0.5] | Light extinction; higher = less deep heating, stronger stratification |
coef_mix_hyp |
[0.3, 0.7] | Hypolimnetic mixing; higher = more deep mixing, warmer hypolimnion |
wind_factor |
[0.7, 1.3] | Wind speed multiplier; higher = more surface mixing |
lw_factor |
[0.7, 1.3] | Longwave radiation multiplier; affects surface energy balance |
ch |
[0.0005, 0.002] | Sensible heat transfer coefficient |
Calibration Strategy
- Start with defaults, run, compute RMSE
- Adjust
Kwfirst (strongest control on stratification) - Then
coef_mix_hyp(controls deep temperatures) - Fine-tune
wind_factorandlw_factorfor surface/overall bias chhas moderate effect on surface heat exchange
RMSE Computation
- Match observations to simulation by exact datetime and rounded depth
- depth_sim = round(lake_depth - z) to get depth from surface
- Overall RMSE, deep (>=13m) RMSE, summer deep (Jun-Sep, >=13m) RMSE
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.
- 3d ago First seen · 28 lines · 20 tokens per session scan A 9402adc32a54
glm-calibration is a skill published in the GitHub repository cxcscmu/SkillLearnBench (83 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 340 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 2026-09-03.
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…
logistics-rules-to-optimization
Translate logistics and operations rules into optimization variables and constraints. Use when an operations problem describes vehicles, routes, depots, pickups, dropoffs, inventory, capacity, assignments, time windows, service targets, penalties, resource limits, or other business rules that need to become an…
mip-solver-and-solution-audit
Operational workflow for hard integer-programming optimization tasks: selecting an installed solver, preserving solver/incumbent certificates, extracting feasible schedules, recomputing metrics from final outputs, and writing consistent reports. Use when a task requires a MIP, solver status, objective value, bound…
lab-unit-harmonization
Comprehensive clinical laboratory data harmonization for multi-source healthcare analytics. Convert between US conventional and SI units, standardize numeric formats, and clean data quality issues. This skill should be used when you need to harmonize lab values from different sources, convert units for clinical…
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.
seisbench-model-api
An overview of the core model API of SeisBench, a Python framework for training and applying machine learning algorithms to seismic data. It is useful for annotating waveforms using pretrained SOTA ML models, for tasks like phase picking, earthquake detection, waveform denoising and depth estimation. For any waveform…