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 OpenLAIR/OpenSkill --skill evo-thermal-sysidgit clone --depth 1 https://github.com/OpenLAIR/OpenSkillWrote 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/openlair/openskill/evo-thermal-sysid)<a href="https://agentmods.dev/skills/openlair/openskill/evo-thermal-sysid"><img src="https://agentmods.dev/badge/skills/openlair/openskill/evo-thermal-sysid/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/openlair/openskill/evo-thermal-sysid"><img src="https://agentmods.dev/badge/skills/openlair/openskill/evo-thermal-sysid.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00049 | $0.00512 |
| Opus 5 | $0.00024 | $0.00256 |
| Sonnet 5 | $0.00010 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
evo-thermal-sysid 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 yesterday.
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
evo-thermal-sysid
System identification for first-order thermal HVAC systems.
Functions
run_calibration_test(sim, heater_power=50.0, duration=60.0)- Run open-loop step test, returns calibration_log dictfirst_order_step_response(t, K, tau, T_amb, U_step)- First-order model: T_amb + KU_step(1-exp(-t/tau))identify_system_params(calibration_log)- Fit K and tau from calibration data using curve_fitfilter_temperature_data(temp_data, window_length=11, polyorder=2)- Savitzky-Golay filtercalculate_fit_metrics(T_actual, T_predicted)- Returns (r_squared, rmse)save_calibration_results(calibration_log, estimated_params)- Save JSON files to /root/
Usage
import sys
sys.path.insert(0, '/app/environment/skills/evo-thermal-sysid/scripts')
from sysid_utils import run_calibration_test, identify_system_params, save_calibration_results
sys.path.insert(0, '/root')
from hvac_simulator import HVACSimulator
sim = HVACSimulator()
calib_log = run_calibration_test(sim, heater_power=50.0, duration=60.0)
params = identify_system_params(calib_log)
save_calibration_results(calib_log, params)
Key Domain Knowledge
- First-order thermal model: dT/dt = (1/tau) * (K*u + T_amb - T)
- Step response: T(t) = T_amb + KU_step(1 - exp(-t/tau))
- K ~ 0.12 C/% power, tau ~ 40s for typical HVAC
- Use Savitzky-Golay filter (preserves exponential shape) not moving average
- Use curve_fit with bounds ([0.001, 1.0], [1.0, 200.0]) and maxfev=10000
- Calibration needs >= 30s duration, >= 20 data points
- R-squared > 0.95 indicates good first-order fit
What ships with it
2 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.
- yesterday First seen · 44 lines · 49 tokens per session scan A 3df09c236884
evo-thermal-sysid is a skill published in the GitHub repository OpenLAIR/OpenSkill (88 stars, last pushed yesterday), licensed Apache-2.0. It adds 49 tokens to every session and 512 once invoked, about $0.0002 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 2026-09-11.
Other skills, from other repositories
fba-simulator
Run Flux Balance Analysis (FBA) and related constraint-based simulations using COBRApy. Covers standard FBA, parsimonious FBA (pFBA), Flux Variability Analysis (FVA), loopless FBA, gene/reaction knockouts, and carbon source swapping. Outputs flux distributions and CSV files.
gsmm-validator
Validate a COBRApy genome-scale metabolic model for mass/charge balance, stoichiometric consistency, biomass producibility, dead-end metabolites, thermodynamic loops, and GPR rule formatting. Outputs a structured validation report with errors and warnings.
gsmm-builder
Build or load a genome-scale metabolic model (GSMM) using COBRApy. Covers loading from BIGG, constructing minimal models from scratch, setting medium constraints, and exporting validated .json model files.
stat-result-validator
Validate statistical research outputs for formulation quality, method-to- problem alignment, theory presence, experimental evidence, fair comparison, artifact completeness, and final-claim consistency.
statistical-theory-analysis
Analyze theoretical properties of statistical methods under the formal formulation: identifiability, bias, variance, consistency, asymptotics, coverage, error bounds, robustness, and limitations.
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.