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 flonat/flonat-research --skill numerical-checkgit clone --depth 1 https://github.com/flonat/flonat-researchWrote 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/flonat/flonat-research/numerical-check)<a href="https://agentmods.dev/skills/flonat/flonat-research/numerical-check"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/numerical-check/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/flonat/flonat-research/numerical-check"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/numerical-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00065 | $0.02185 |
| Opus 5 | $0.00032 | $0.01092 |
| Sonnet 5 | $0.00013 | $0.00437 |
| Haiku 4.5 | $0.00006 | $0.00218 |
Grade A, and why
numerical-check 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 7d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Numerical Check: Falsify a Self-Authored Math Claim by Sweep
Empirically stress-test a mathematical claim you wrote but have not proven. The goal is falsification: throw many random instances at the claim and try to break it. A single genuine counterexample kills the claim; a large clean sweep is evidence, never proof.
When to Use
- You wrote a Proposition / Theorem / Conjecture (monotonicity, threshold, comparative-static, inequality, closed-form, limit) and want to know if it's actually true before claiming it.
numerical-check, "stress-test my conjecture", "find a counterexample to X", "is Q(ρ) really monotone", "does the threshold hold for all …".- The write-time empirical arm of the
mark-unverifiedrule (self-authored math must be checked before assertion).
When NOT to Use
| Situation | Use instead |
|---|---|
| Verify an algebra / derivative / limit / closed-form identity | symbolic-check (R2) |
| Machine-prove a lemma (want a proof, not a stress-test) | lean-check (R3) |
| Re-verify a computed empirical result in another language | cross-language-check |
| Conceptual / assumption-completeness review | domain-reviewer (agent) |
Position in the verification spectrum
R1 — numerical falsification. Can FALSIFY definitively (a confirmed counterexample refutes the claim) but can never VERIFY (no counterexample ≠ proof). The strongest positive result is INCONCLUSIVE (supported): no counterexample in N draws. Pair with lean-check (R3) to prove the claim once it survives.
Procedure
1. Formalize the claim as a predicate over a domain
Restate the claim as P(x) that must hold for all x in a domain D. Make the failure condition explicit and quantitative.
- "Q(ρ) is monotone decreasing in ρ" →
P(instance) := max_i (Q(ρ_{i+1}) − Q(ρ_i)) ≤ tolover a ρ-grid. - "threshold ρ* separates help/hurt" →
P := (Q<p_max) iff (ρ>ρ*). - Write down the domain
Dprecisely (which parameters, which ranges, which side-conditions — e.g. "mean competence > ½, dispersed").
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.
- 7d ago First seen · 134 lines · 65 tokens per session scan A fbb2917118d5
numerical-check is a skill published in the GitHub repository flonat/flonat-research (133 stars, last pushed 16d ago), licensed MIT. It adds 65 tokens to every session and 2,185 once invoked, about $0.0003 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
latex-compile
Compile a LaTeX document and fix every error plus aesthetic issue (overfull/underfull boxes, widows, alignment, fonts) for a clean PDF and log. Use this instead of running pdflatex/latexmk manually — it avoids the latexmk stale-log trap and silent grep failures on binary log output, and it reformats rather than…
nb-to-wolfbook
Convert Mathematica .nb or .m files to Wolfbook .wb format so they open and run in VS Code. Use when bringing existing .nb/.m files into Wolfbook, or to make an existing .wb bridge-safe.
sync-wb-nb
Propagate a change made in a Wolfbook .wb notebook into the paired .nb notebook so the two stay identical. Use immediately after every .wb edit.
wolfram-headless
Run heavy Wolfram Language (wolframscript) computations from Claude Code reliably, and diagnose the misleading "The product exited because of a license error". Use whenever invoking wolframscript on a non-trivial computation, when a wolframscript job dies with a "license error" despite a valid license, or when Wolfram…
cross-validate
Format a result, derivation, or numerical value for independent verification by a second model. Use when you want a cross-check on an important or contested result.
verify-citation
Confirm a paper actually exists (arXiv / Semantic Scholar / OpenAlex) before citing it. Use before writing any new citation.