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 LuuOW/meridian-mcp --skill physics-units-sigit clone --depth 1 https://github.com/LuuOW/meridian-mcpWrote 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/luuow/meridian-mcp/physics-units-si)<a href="https://agentmods.dev/skills/luuow/meridian-mcp/physics-units-si"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/physics-units-si/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/luuow/meridian-mcp/physics-units-si"><img src="https://agentmods.dev/badge/skills/luuow/meridian-mcp/physics-units-si.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 | $0.00096 | $0.02086 |
| Opus 5 | $0.00048 | $0.01043 |
| Sonnet 5 | $0.00019 | $0.00417 |
| Haiku 4.5 | $0.00010 | $0.00209 |
Grade A, and why
physics-units-si 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 10d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
physics-units-si
When to invoke
- Parsing physics abstracts or papers for numerical quantities
- Converting between units in a calculation
- Validating that a computed quantity has the expected dimension
- Building a regex/parser that extracts "100 GeV" or "4.7 GHz" from free text
- Writing output that mixes orders of magnitude (always show canonical form)
Canonical base-unit table
Energy — base: GeV (high-energy physics convention) OR joule (SI).
| Unit | SI (joules) | GeV |
|---|---|---|
| eV | 1.602176634e-19 | 1e-9 |
| keV | 1.602176634e-16 | 1e-6 |
| MeV | 1.602176634e-13 | 1e-3 |
| GeV | 1.602176634e-10 | 1.0 |
| TeV | 1.602176634e-7 | 1e3 |
| PeV | 1.602176634e-4 | 1e6 |
| EeV | 0.1602176634 | 1e9 |
| erg | 1e-7 | 6.242e2 |
| joule | 1 | 6.242e9 |
Frequency — base: Hz.
| Unit | Hz |
|---|---|
| Hz | 1 |
| kHz | 1e3 |
| MHz | 1e6 |
| GHz | 1e9 |
| THz | 1e12 |
| PHz | 1e15 |
Length — base: meter.
| Unit | meters |
|---|---|
| fm | 1e-15 |
| pm | 1e-12 |
| Å | 1e-10 |
| nm | 1e-9 |
| μm / um | 1e-6 |
| mm | 1e-3 |
| cm | 1e-2 |
| km | 1e3 |
| au | 1.495978707e11 |
| ly | 9.4607304725808e15 |
| pc | 3.0856775814913673e16 |
Mass — base: kg.
| Unit | kg |
|---|---|
| u (atomic) | 1.66053906892e-27 |
| g | 1e-3 |
| ton | 1e3 |
| solar mass (M☉) | 1.98892e30 |
Time — base: second.
Standard SI prefixes apply (fs, ps, ns, μs, ms, s, min=60 s, h=3600 s, day=86400 s, yr≈3.155693e7 s).
CODATA constants (memorize — 2018 CODATA values)
| Symbol | Name | Value |
|---|---|---|
| c | Speed of light in vacuum | 299792458 m/s (exact, SI defn) |
| h | Planck constant | 6.62607015e-34 J·s (exact) |
| ℏ | Reduced Planck | 1.054571817e-34 J·s |
| e | Elementary charge | 1.602176634e-19 C (exact) |
| G | Gravitational const | 6.67430e-11 m³/(kg·s²) (±2.2e-15) |
| k_B | Boltzmann | 1.380649e-23 J/K (exact) |
| N_A | Avogadro | 6.02214076e23 /mol (exact) |
| α | Fine-structure | 7.2973525693e-3 (≈1/137.035999) |
| m_e | Electron mass | 9.1093837015e-31 kg = 0.51099895 MeV/c² |
| m_p | Proton mass | 1.67262192369e-27 kg = 938.27208816 MeV/c² |
| m_n | Neutron mass | 1.67492749804e-27 kg = 939.56542052 MeV/c² |
| R_∞ | Rydberg | 1.0973731568160e7 /m |
| σ | Stefan-Boltzmann | 5.670374419e-8 W/(m²·K⁴) |
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.
- 10d ago First seen · 145 lines · 96 tokens per session scan A 6c2fcc644e01
physics-units-si is a skill published in the GitHub repository LuuOW/meridian-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 2,086 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
physicsnemo-discover
Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…
fenics-fem
Use this Skill to solve PDEs with the finite element method using FEniCS/dolfinx: weak form formulation, mesh generation with gmsh, Poisson/elasticity problems, boundary conditions, and paraview export.
arxiv-search
Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.
arxiv-search
Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.
arxiv-search
Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.
arxiv-search
Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.