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.
npx skills add beita6969/ScienceClaw --skill lean4-provergit clone --depth 1 https://github.com/beita6969/ScienceClawWrote 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.
[](https://agentmods.dev/skills/beita6969/scienceclaw/lean4-prover)<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.
<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>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.
| Model | Per session | Once 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 |
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 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
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.
- 9d ago First seen · 158 lines · 54 tokens per session scan C c68dcf6d7713
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.
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…
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…
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.
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…
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.
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.