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/vantasnerdan/substrate-framework/small-ratio-numericsnpx skills add vantasnerdan/substrate-framework --skill small-ratio-numericsgit clone --depth 1 https://github.com/vantasnerdan/substrate-frameworkWrote 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/vantasnerdan/substrate-framework/small-ratio-numerics)<a href="https://agentmods.dev/skills/vantasnerdan/substrate-framework/small-ratio-numerics"><img src="https://agentmods.dev/badge/skills/vantasnerdan/substrate-framework/small-ratio-numerics.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 | $0.00170 | $0.05365 |
| Opus 5 | $0.00085 | $0.02683 |
| Sonnet 5 | $0.00034 | $0.01073 |
| Haiku 4.5 | $0.00017 | $0.00536 |
Grade A, and why
small-ratio-numerics 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.
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.
Small-Ratio Numerics
A synthesis of how communities that live in the small-ratio regime — nuclear Skyrme, baby-Skyrme, magnetic skyrmions, Einstein–Skyrme, boson stars, liquid-crystal defect energetics — handle a problem that defeats naive single-grid minimization. The recurring pattern: a strong short-distance scale sets the core and the bulk of the energy; a much weaker long-distance scale carries the physics you care about; the question (a soft Hessian eigenvalue, a tiny energy difference, a weak force) lives in the gap between them. Once $\varepsilon$ or $\lambda_{\min}/\lambda_2$ drops below ~1e-3, the weak signal is usually smaller than truncation error on any single grid, and the calculation reports spurious instability, wrong force signs, runaway frequencies, or "minima" that move with the box.
The field's response was not more precision — it was splitting the question into pieces that each have a well-conditioned answer. That split, and the techniques around it, is what this skill shares. It is advice, not a work plan; pick the pieces that fit the situation. (Origin: the methods note in issue #155 and the literature it cites.)
Eligibility before precision
Do not form a Hessian, generalized eigenproblem, fixed-$J$ functional, force, splitting, or radiation threshold until the mathematical object, ensemble, admissible representation, and observable have earned their upstream licenses. The background must satisfy the correct Euler–Lagrange equations in the claimed function space; record both its residual and a conditioning-aware forward-error estimate. Build the full second variation by differentiating the complete functional before restricting zero-valued fields or blocks. Declare the constrained tangent space, gauges and moduli, kinetic-metric rank and sign, asymptotic operator, and essential-spectrum threshold.
For a collective clock, first establish a globally defined compact action,
fixed period and generator normalization, action invariance, vacuum fixation,
conserved Noether charge, and nondegenerate Legendre map. Only then may “fix
$J$” mean minimization on a physical fixed-charge manifold. A localized
positive-norm eigenmode establishes MODE_EXISTS; it does not establish a
cyclic phase, Noether charge, fixed-$J$ clock, or nonlinear periodic orbit.
What ships with it
1 file 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.
- 3d ago First seen · 145 lines · 170 tokens per session scan A ac221cf45eb0
small-ratio-numerics is a skill published in the GitHub repository vantasnerdan/substrate-framework (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 170 tokens to every session and 5,365 once invoked, about $0.0009 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
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…
nature-statistics
Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model…
evaluating-with-leakage-gates
Evaluate an OpenMed de-identification or clinical NER model against the leakage-first release gates G1a through G8, which gate releases on residual PHI leakage rather than on F1. Use when the user wants to run the OpenMed eval harness on a synthetic golden set, decide whether a de-id model is RELEASABLE or…
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…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
indication-dossier
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.