lean4-prover

lean4-prover is a skill for Claude Code, Codex from beita6969/ScienceClaw. It costs 54 tokens per session (1,220 once invoked), scanned C, original, MIT.

A guide to Lean 4, a tool for formally proving mathematical statements and checking that proofs or program properties are correct.

In plain words
What is it for?
Use it for theorem proving, formalized mathematics, type-theory exploration, proof search, and program verification.
Why use it?
It helps catch gaps in mathematical reasoning by requiring proofs that the system can verify.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it for theorem proving, formalized mathematics, type-theory exploration, proof search, and program verification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/beita6969/scienceclaw/lean4-prover
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 beita6969/ScienceClaw --skill lean4-prover
Clone the repo
git clone --depth 1 https://github.com/beita6969/ScienceClaw

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 lean4-prover

README.md
[![agentmods](https://agentmods.dev/badge/skills/beita6969/scienceclaw/lean4-prover/github.svg)](https://agentmods.dev/skills/beita6969/scienceclaw/lean4-prover)
Your own site
<a href="https://agentmods.dev/skills/beita6969/scienceclaw/lean4-prover"><img src="https://agentmods.dev/badge/skills/beita6969/scienceclaw/lean4-prover/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 lean4-prover

Your own site · 80×15
<a href="https://agentmods.dev/skills/beita6969/scienceclaw/lean4-prover"><img src="https://agentmods.dev/badge/skills/beita6969/scienceclaw/lean4-prover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,220 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00054 $0.01220
Opus 5 $0.00027 $0.00610
Sonnet 5 $0.00011 $0.00244
Haiku 4.5 $0.00005 $0.00122

Measured 9d ago against content hash c68dcf6d7713, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

lean4-prover scanned grade C with 2 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 9d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl https://elan.lean-lang.org/install.sh -sSf | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl https://elan.lean-lang.org/install.sh -sSf | sh
skills/lean4-prover/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lean 4 Theorem Prover

Formal theorem proving, mathematical verification, proof search, and type theory exploration.

When to Use / When NOT to Use

Use when: formal theorem proving, mathematical verification, proof search, type-theoretic reasoning, formalized mathematics with Mathlib, program verification.

NOT for: numerical computation (use scipy/numpy), symbolic algebra or calculus (use sympy), statistical analysis (use statsmodels), quick calculations.

Installation

If lean is not available, install via elan (the Lean version manager):

curl https://elan.lean-lang.org/install.sh -sSf | sh
# or on macOS:
brew install elan-init
elan default leanprover/lean4:stable

Basic Theorem Structure

-- Simple proposition proof
theorem my_first_theorem : 1 + 1 = 2 := by
  rfl

-- Implication
theorem modus_ponens (P Q : Prop) (hp : P) (hpq : P → Q) : Q := by
  apply hpq
  exact hp

-- Universal quantifier
theorem add_comm_example : ∀ (a b : Nat), a + b = b + a := by
  intro a b
  omega

Core Tactics

-- intro: introduce hypotheses / universally quantified variables
-- apply: apply a function or lemma to the goal
-- exact: provide the exact proof term
-- rfl: reflexivity (proves a = a or definitional equalities)
-- simp: simplification using simp lemmas
-- ring: prove equalities in commutative rings
-- omega: decide linear arithmetic over Nat and Int
-- linarith: linear arithmetic reasoning with hypotheses
-- cases / rcases: case split on inductive types
-- induction: structural induction
-- constructor: prove a conjunction or existential
-- contradiction: close goal from contradictory hypotheses

-- Example combining tactics
theorem example_proof (n : Nat) (h : n > 0) : n + n > n := by
  linarith

theorem ring_example (a b : Int) : (a + b) ^ 2 = a ^ 2 + 2 * a * b + b ^ 2 := by
  ring

Project Setup with Lakefile

# Create a new Lean 4 project
lake new my_project
cd my_project

# Project structure:
# my_project/
#   lakefile.lean      -- build config
#   lean-toolchain     -- Lean version
#   MyProject/
#     Basic.lean       -- source files

Read the full file on GitHub · 158 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. 9d ago First seen · 158 lines · 54 tokens per session scan C c68dcf6d7713

Subscribe to this mod's changes

lean4-prover is a skill published in the GitHub repository beita6969/ScienceClaw (898 stars, last pushed 3mo ago), licensed MIT. It adds 54 tokens to every session and 1,220 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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

biopython

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use…

synthetic-sciences/openscience · 76 tokens

scanpy

Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use…

synthetic-sciences/openscience · 68 tokens

structure-prediction

Protein structure prediction from sequence. ESMFold-based, single GPU, no MSA needed. Predicts 3D structures with pLDDT confidence scores for drug discovery targets.

synthetic-sciences/openscience · 42 tokens

biomcp

Search and retrieve biomedical data - genes, variants, clinical trials, diagnostic tests, articles, drugs, diseases, pathways, proteins, adverse events, pharmacogenomics, and phenotype-disease matching. Use for gene function, variant pathogenicity, trials, diagnostics, drug safety, pathway context, disease workups…

genomoncology/biomcp · 70 tokens

biomcp-research

Do biomedical literature and variant research with the BioMCP CLI, and file what you learn about the tool itself as issues in the biomcp repo.

genomoncology/biomcp · 36 tokens

biological-expert

Expert-level biology, biotechnology, genetics, bioinformatics, and computational biology. Use when the user mentions biology, biotechnology, genetics, bioinformatics, or genomics, or when the task involves Molecular Biology, Genomics & Bioinformatics, Systems Biology, or Data Analysis.

personamanagmentlayer/pcl · 59 tokens