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 nimabahrami/pypsa-skills-kit --skill pypsa-physical-realismgit clone --depth 1 https://github.com/nimabahrami/pypsa-skills-kitWrote 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/nimabahrami/pypsa-skills-kit/pypsa-physical-realism)<a href="https://agentmods.dev/skills/nimabahrami/pypsa-skills-kit/pypsa-physical-realism"><img src="https://agentmods.dev/badge/skills/nimabahrami/pypsa-skills-kit/pypsa-physical-realism/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/nimabahrami/pypsa-skills-kit/pypsa-physical-realism"><img src="https://agentmods.dev/badge/skills/nimabahrami/pypsa-skills-kit/pypsa-physical-realism.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 | $0.00138 | $0.00938 |
| Opus 5 | $0.00069 | $0.00469 |
| Sonnet 5 | $0.00028 | $0.00188 |
| Haiku 4.5 | $0.00014 | $0.00094 |
Grade A, and why
pypsa-physical-realism 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 11d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PyPSA Physical Realism
Model solves != model right. Skill = linter: deterministic checks -> judgment on rest.
Script first
python scripts/validate_network.py path/to/network.nc # or CSV folder
python scripts/validate_network.py network.nc --strict # warnings fail too
- CHECK: structural invariants + parameter ranges. Exits nonzero on ERROR.
- REPORT: findings grouped by severity + fix each.
- input TIME-SERIES forensics (timezone | leap | placeholder profiles) = pypsa-data-pipelines scripts/audit_inputs.py — run both before real decisions.
Script invariants = review checklist
- no free energy: Link efficiency > 1 only ambient-heat carriers (heat pumps) | Generator efficiency in (0, 1] | no negative standing losses.
- no free machines: extendable -> capital_cost > 0. ! Overnight-CAPEX-sized capital_cost -> flagged probably-not-annualized (generators + links). committable+extendable -> ERROR on PyPSA 1.0.x | WARN >=1.1.0 (big-M).
- real inputs cost money: conversion tech (electrolysis | fuel cells | methanation | DAC | ...) with marginal_cost == 0 -> flag. Water, sorbents, stack/catalyst degradation real. Zero-VOM defensible only for wires.
- topology: no orphan buses | no loads on suspicious carriers | no zero-impedance lines | no bidirectional lossy links (p_min_pu < 0 with efficiency < 1).
- time accounting: snapshot weighting columns consistent | cyclic storage set on full-year runs.
- carbon accounting: fossil carriers carry co2_emissions; 0 -> flag. CO2-chain tech (CCS|DAC|synfuels) w/o explicit co2 bus -> flag (! Link carrier co2_emissions NOT counted by GlobalConstraints). >1 heat load carrier per bus -> temperature-mixing flag.
- range screening: efficiencies | standing losses | costs inside ranges from references files below.
Judgment checks beyond script
- merged buses hiding congestion relevant to THIS question? -> pypsa-market-design.
- VERIFY: VRE capacity factors per region. Europe: wind onshore 0.20-0.40 | offshore 0.35-0.55 | solar 0.10-0.22. Wrong cutout year | unit confusion shows here first.
- post-solve smells: storage round-trips creating energy | shadow prices 0 all hours (load not binding) | single technology absorbs whole expansion (missing p_nom_max | cost typo). Visual form -> pypsa-reporting diagnostic panel.
- LOPF = MW-only -> optimized dispatch may be AC-infeasible. Post-solve n.pf/n.lpf screens + applicability gate + escalation boundary -> references/power-flow-checks.md.
What ships with it
6 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.
- 11d ago First seen · 52 lines · 0 tokens per session scan A 8f2e8d9b6980
pypsa-physical-realism is a skill published in the GitHub repository nimabahrami/pypsa-skills-kit (23 stars, last pushed 3mo ago), licensed MIT. It adds 138 tokens to every session and 938 once invoked, about $0.0007 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…