math-proof

math-proof is a skill for Claude Code, Codex from morankor/theorist-toolbox. It costs 64 tokens per session (696 once invoked), scanned A, original, MIT.

A tool for writing complete mathematical proofs for research papers, with every algebraic step, assumption, sign, and edge case stated clearly.

In plain words
What is it for?
Use it to prove theorems, derive results, check claims, or turn economic and game-theory reasoning into formal proofs.
Why use it?
It helps remove gaps and hand-waving from proof sketches so a reader can check the argument without filling in missing steps.

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/morankor/theorist-toolbox/math-proof
Any agent
npx skills add morankor/theorist-toolbox --skill math-proof
Clone the repo
git clone --depth 1 https://github.com/morankor/theorist-toolbox

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-proof

README.md
[![agentmods](https://agentmods.dev/badge/skills/morankor/theorist-toolbox/math-proof.svg)](https://agentmods.dev/skills/morankor/theorist-toolbox/math-proof)
Your own site
<a href="https://agentmods.dev/skills/morankor/theorist-toolbox/math-proof"><img src="https://agentmods.dev/badge/skills/morankor/theorist-toolbox/math-proof.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 696 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 $0.00064 $0.00696
Opus 5 $0.00032 $0.00348
Sonnet 5 $0.00013 $0.00139
Haiku 4.5 $0.00006 $0.00070

Measured 6d ago against content hash bcbef5f11a5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

math-proof 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 6d 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.

codex/.agents/skills/math-proof/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Math Proof

Write proofs suitable for a paper draft. The deliverable is a complete proof, not an outline. Every transition must be checkable by a skeptical reader without filling in missing algebra, sign arguments, or quantifier choices.

This skill adapts Moran Koren's Theorist Toolbox proof discipline for Codex. Preserve the core invariant: if a step is not proved, cited, or explicitly marked as conjectural, do not present it as established.

Workflow

  1. Parse the exact claim, hypotheses, domains, and conclusion.
  2. State the proof plan before proving: direct proof, contradiction, induction, fixed point, comparative statics, counterexample search, or case split.
  3. Define all notation before use. Give object types and parameter domains.
  4. Prove one numbered step at a time. Each step must open with what it will show.
  5. Show intermediate algebra. Do not jump from setup to simplified result.
  6. Sign every derivative, inequality, monotonicity claim, and limit claim at the line where it appears.
  7. Handle edge cases and boundary behavior explicitly.
  8. Separate proved results from conjectures, examples, and numerical evidence.
  9. End with a short intuition paragraph when useful, then close the proof with \square.

Proof Discipline

  • Use \triangleq for definitions and = for equalities.
  • Use display math for multi-term expressions, ratios, derivatives, thresholds, and relation chains.
  • Before algebra, say the goal: "It remains to show that ...".
  • When differentiating a ratio, compute numerator and denominator derivatives before applying the quotient rule.
  • When manipulating inequalities, state why the inequality direction is preserved or reversed.
  • If a threshold is integer-valued but differentiated as continuous, flag the relaxation and explain how discreteness affects the claim.
  • When invoking a theorem, instantiate it in the paper's notation. If the theorem is not standard, cite it precisely or prove the needed lemma.
  • Never prove the general case by checking examples. Examples are evidence, not proof.

Read the full file on GitHub · 82 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. 6d ago First seen · 82 lines · 64 tokens per session scan A bcbef5f11a5b

Subscribe to this mod's changes

math-proof is a skill published in the GitHub repository morankor/theorist-toolbox (69 stars, last pushed 27d ago), licensed MIT. It adds 64 tokens to every session and 696 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 2026-08-30.

Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

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…

K-Dense-AI/scientific-agent-skills · 83 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

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…

maziyarpanahi/openmed · 205 tokens