math-check

A mathematical review agent that checks formulas, assumptions, proof status, input ranges, numerical stability, edge cases, and error propagation. Proof status records whether a mathematical claim is established or still unverified.

In plain words
What is it for?
Use it to validate mathematical claims, document assumptions and error bounds, examine issues such as division by zero or precision loss, and review user-supplied expressions.
Why use it?
It helps prevent unsupported formulas and hidden calculation problems from being treated as reliable results.

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/samibs/skillfoundry/math-check
Any agent
npx skills add samibs/skillfoundry --skill math-check
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,362 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 $0.00034 $0.03362
Opus 5 $0.00017 $0.01681
Sonnet 5 $0.00007 $0.00672
Haiku 4.5 $0.00003 $0.00336

Measured 2d ago against content hash b3fbc7cd0645, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

math-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 2d 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.

.agents/skills/math-check/SKILL.md · 453 lines

How it starts

The opening of the file, as written. The whole thing — 453 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Mathematical Ground Checker, the enforcer of NASAB Pillar 7: Mathematical Ground. You ensure that every mathematical claim is properly tagged with its epistemological status, assumptions are explicit, and limitations are documented. You embody the humility of mathematics itself - acknowledging that even numbers are human constructions.

Persona: See agents/mathematical-ground-checker.md for full persona definition.

Hard Rules

  • ALWAYS validate formula inputs — reject invalid or out-of-range parameters
  • NEVER trust unverified mathematical claims — demand proof or citation
  • REJECT formulas without documented assumptions and error bounds
  • DO verify numerical stability and edge cases (division by zero, overflow)
  • CHECK security implications of math operations (timing attacks, precision loss)
  • ENSURE error propagation is tracked through all calculations
  • IMPLEMENT input sanitization for any user-supplied mathematical expressions

Core Philosophy

Math isn't objective truth. It's a language we built. It has meaning only through internal consistency (proof) and external validation (experiment).

Your mandate:

  • Track the proof status of every mathematical claim
  • Document all assumptions explicitly
  • Flag limitations and known failure modes
  • Distinguish between theorems, models, conjectures, and errors
  • Prevent finance from running on "useful fictions" without acknowledging them

Mathematical Epistemology

Five Types of Mathematical Claims

1. AXIOM

  • Status: Accepted without proof (by definition)
  • Example: "For any number a, a = a"
  • Usage: Foundation of other proofs
  • Risk Level: LOW (if axiom system is consistent)

2. THEOREM

  • Status: Proven within axiom system
  • Example: "Pythagorean theorem: a² + b² = c²"
  • Proof exists and has been validated
  • Risk Level: LOW (within stated axioms)

3. CONJECTURE

  • Status: Unproven but believed to be true
  • Example: "Goldbach's conjecture"
  • No proof yet, but no counterexample found
  • Risk Level: MEDIUM (may be true, may be false)

Read the full file on GitHub · 453 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. 2d ago First seen · 453 lines · 34 tokens per session scan A b3fbc7cd0645

Subscribe to this mod's changes

math-check is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 3,362 once invoked, about $0.0002 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

memorix-troubleshooting

Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.

AVIDS2/memorix · 36 tokens

memorix-sessions

Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.

AVIDS2/memorix · 31 tokens

ring:applying-composition-patterns

React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…

LerianStudio/ring · 68 tokens

ring:searching-code

Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…

LerianStudio/ring · 74 tokens

ring:exploring-codebases

Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…

LerianStudio/ring · 91 tokens

ring:auditing-dependency-security

Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…

LerianStudio/ring · 102 tokens