verify-math

verify-math is a skill for Claude Code from flonat/flonat-research. It costs 85 tokens per session (1,893 once invoked), scanned A, original, MIT.

A routing and reporting workflow for checking mathematical claims. It sends the claim to suitable reviewers, calculations, symbolic tools, or Lean, then combines their findings.

In plain words
What is it for?
Use it to verify a theorem, proposition, conjecture, or mathematical argument from an entire paper.
Why use it?
It helps avoid relying on one kind of check when a theorem or paper may contain several different types of errors.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; $skill-name invocation.

Good fit Use it to verify a theorem, proposition, conjecture, or mathematical argument from an entire paper.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/flonat/flonat-research/verify-math
Install

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.

Any agent
npx skills add flonat/flonat-research --skill verify-math
Clone the repo
git clone --depth 1 https://github.com/flonat/flonat-research

Made for: Claude Code.

Wrote 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.

agentmods badge for verify-math

README.md
[![agentmods](https://agentmods.dev/badge/skills/flonat/flonat-research/verify-math/github.svg)](https://agentmods.dev/skills/flonat/flonat-research/verify-math)
Your own site
<a href="https://agentmods.dev/skills/flonat/flonat-research/verify-math"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/verify-math/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.

agentmods 80×15 button for verify-math

Your own site · 80×15
<a href="https://agentmods.dev/skills/flonat/flonat-research/verify-math"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/verify-math.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,893 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00085 $0.01893
Opus 5 $0.00043 $0.00946
Sonnet 5 $0.00017 $0.00379
Haiku 4.5 $0.00009 $0.00189

Measured 8d ago against content hash c29c2ed7727f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

verify-math 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/extract_block.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/verify-math/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Math: Route a Math Claim Through the Verification Spectrum

The front door for verifying self-authored mathematics. Classify each claim, dispatch it to the strongest applicable rung(s), and merge the sub-verdicts into one report. This skill does not verify anything itself — it routes and aggregates; the rungs do the work.

When to Use

  • You have a Proposition / Theorem / Conjecture (or a whole paper's worth) and want it verified with the right method(s), possibly combined.
  • verify-math, "verify this theorem", "check all the math in the paper", "is this result correct".
  • The operational front end of mark-unverified: run this before asserting a self-authored result.

When NOT to Use

  • You already know the single method → call it directly (numerical-check, symbolic-check, lean-check, or domain-reviewer).
  • Non-mathematical claims (citations, prose) → proofread, bib-validate, domain-reviewer.

The verification spectrum (the rungs it routes to)

Rung Method Can it… Tool
R0 adversarial deductive read catch conceptual/assumption gaps (no proof) domain-reviewer (agent)
R1 numerical falsification falsify definitively; support (never prove) numerical-check
R2 symbolic / CAS prove or falsify an algebra step symbolic-check
R3 formal Lean proof prove (strongest) lean-check

Procedure

1. Decompose the result into atomic claims

A theorem is usually several obligations. List each separately: the algebra steps, the distributional/parameter-space claims, the load-bearing lemma, the conceptual assumptions. Verify each with the rung that fits — a single "verdict" on a compound theorem hides which part is shaky.

When the claim lives in LaTeX, extract a self-contained theorem/proof block before dispatch:

uv run python <skill-dir>/scripts/extract_block.py paper/sections/model.tex "prop:concavity"

The helper includes an immediately following proof and any displayed equations referenced by label. Inspect the output and add missing definitions or assumptions before giving it to a reviewer or computational rung.

Read the full file on GitHub · 125 lines

Files

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.

Changes

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.

  1. 8d ago First seen · 125 lines · 85 tokens per session scan A c29c2ed7727f

Subscribe to this mod's changes

verify-math is a skill published in the GitHub repository flonat/flonat-research (133 stars, last pushed 16d ago), licensed MIT. It adds 85 tokens to every session and 1,893 once invoked, about $0.0004 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.

Related

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…

Mexregkan/claude-for-researchers · 79 tokens

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.

Mexregkan/claude-for-researchers · 53 tokens

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.

Mexregkan/claude-for-researchers · 38 tokens

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…

Mexregkan/claude-for-researchers · 84 tokens

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.

Mexregkan/claude-for-researchers · 36 tokens

verify-citation

Confirm a paper actually exists (arXiv / Semantic Scholar / OpenAlex) before citing it. Use before writing any new citation.

Mexregkan/claude-for-researchers · 31 tokens