math-auditor

math-auditor is a skill for Claude Code, Codex from CliMA/EnsembleKalmanProcesses.jl. It costs 167 tokens per session (2,396 once invoked), scanned A, original, Apache-2.0.

An adversarial review of a Julia package's mathematical code and tests. Julia is a programming language often used for scientific computing; adversarial review means actively trying to find errors.

In plain words
What is it for?
Use it to check scientific Julia packages, cite mathematical problems by file and line, describe failure cases, and produce focused prompts for fixing confirmed issues.
Why use it?
It helps catch incorrect equations, statistical mistakes, inconsistent conventions, and bugs that ordinary code review may miss.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/clima/ensemblekalmanprocesses.jl/math-auditor
Any agent
npx skills add CliMA/EnsembleKalmanProcesses.jl --skill math-auditor
Clone the repo
git clone --depth 1 https://github.com/CliMA/EnsembleKalmanProcesses.jl

Made for: Claude Code, Codex.

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 math-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/clima/ensemblekalmanprocesses.jl/math-auditor.svg)](https://agentmods.dev/skills/clima/ensemblekalmanprocesses.jl/math-auditor)
Your own site
<a href="https://agentmods.dev/skills/clima/ensemblekalmanprocesses.jl/math-auditor"><img src="https://agentmods.dev/badge/skills/clima/ensemblekalmanprocesses.jl/math-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 167 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,396 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00167 $0.02396
Opus 5 $0.00084 $0.01198
Sonnet 5 $0.00033 $0.00479
Haiku 4.5 $0.00017 $0.00240

Measured 5d ago against content hash 90ba4d80e66d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

math-auditor 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 5d 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.

.claude/skills/math-auditor/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Math Audit

Adversarial review of a scientific Julia package for mathematical accuracy and consistency — not software architecture (flag architecture only when it causes mathematical wrongness, e.g. mutation aliasing, accidental type demotion, or inconsistent conventions between modules).

The output is written for the package's own developers: findings must cite exact file:line, state the correct mathematics, and give a concrete failure scenario. A finding that can't survive an attempt at refutation doesn't ship.

What "adversarial" means here

Each reviewer's job is to break the code, not describe it. Concretely, hunt for:

  • Wrong equations: update formulas, gradients, covariances, likelihoods that differ from the cited papers or from the docstring's own LaTeX. Derive the correct expression independently and diff it against the code.
  • Convention drift: rows-vs-columns for ensemble members, N-1 vs N normalization, factor-of-2 / sign errors, Cholesky L vs U, covariance vs precision, whether noise is added in obs-space or transformed space — especially inconsistencies between modules that must agree.
  • Statistical validity: is added noise sampled with the right covariance and scaling (e.g. Δt scaling in stochastic dynamics)? Are means/covariances computed over the right dimension? Deterministic vs stochastic variants actually equivalent in expectation?
  • Numerical soundness: unguarded inv/\ on possibly-singular matrices, loss of symmetry/PSD-ness, subtraction-based variance formulas, missing regularization, sqrt of negative-by-roundoff eigenvalues.
  • Edge cases the math must survive: ensemble size 1–2, dimension 1 (scalar vs matrix degeneracy), zero variance, NaN/failed ensemble members, empty minibatches.
  • Test-math consistency: do the tests actually pin the mathematics (analytic solutions, invariants, convergence rates), or just check shapes and "it runs"? A wrong equation whose test only checks size() is a double finding: the bug and the missing test.

Read the full file on GitHub · 197 lines

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. 5d ago First seen · 197 lines · 167 tokens per session scan A 90ba4d80e66d

Subscribe to this mod's changes

math-auditor is a skill published in the GitHub repository CliMA/EnsembleKalmanProcesses.jl (124 stars, last pushed 4d ago), licensed Apache-2.0. It adds 167 tokens to every session and 2,396 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

qdash

Work with a running QDash instance through qdash-client and saved local profiles. Use when an agent needs to inspect chips, metrics, task results, calibration data, provenance, issues, flows, executions, project files, project-scoped QDash API data, or OpenAPI endpoints from QDash using qdash-client…

oqtopus-team/qdash · 104 tokens

bnlearn

Use this skill when working with bnlearn, a Python library for Bayesian networks, probabilistic graphical models, causal discovery, parameter learning, structure learning, inference, sampling, and directed acyclic graphs (DAG).

erdogant/bnlearn · 46 tokens

audit-post

The end-to-end procedure for auditing one already-published post to a scientific-organization standard. It chains the adversarial skills and — critically — re-runs the auditor on the CORRECTED post to confirm it now passes clean before committing. We are a scientific organization; we do not ship missteps. Run EVERY…

DanceNitra/agora · 0 tokens

falsify

The scientific thinking protocol for AI agents. Use when facing complex, ambiguous, or high-stakes questions where guessing is costly — technical design decisions, architecture choices, debugging theories, data claims, security judgments, or any answer the agent is tempted to give confidently without evidence.…

263311487-ux/falsify · 130 tokens

geo-infer

Geospatial Active Inference framework with 44 modules for ecological, civic, and commercial spatial analysis. Use when working with geospatial data, Active Inference, Bayesian modeling, H3 hexagonal indexing, spatial statistics, or any domain-specific geographic analysis (agriculture, health, economics, risk, climate…

ActiveInferenceInstitute/GEO-INFER · 76 tokens

geo-infer-act

Canonical GEO-INFER Active Inference implementation. Use when implementing or reviewing free-energy minimization, belief updating, generative models, policy selection, H3/spatial active inference, or typed ACT diagnostics.

ActiveInferenceInstitute/GEO-INFER · 46 tokens