alethfeld: Command for Claude Code

.claude/commands/edn-to-lean.md

edn-to-lean is a command for Claude Code from tobiasosborne/alethfeld. It costs 10 tokens per session (588 once invoked), scanned A, original, MIT.

A converter that turns an EDN proof—a structured description of a mathematical proof—into Lean 4 code, a format that can be checked by the Lean theorem prover.

In plain words
What is it for?
Use it when you have an Alethfeld EDN proof file and want a starting Lean 4 formalization, including mapped types and proof tactics.
Why use it?
It reduces the manual work of rewriting theorem statements, types, assumptions, and proof steps in Lean. The generated proof may still contain unfinished parts to complete.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is tobiasosborne/alethfeld's own configuration. It tells Claude Code how to work on alethfeld itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything alethfeld configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tobiasosborne/alethfeld. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tobiasosborne/alethfeld/legacy/.claude/commands/edn-to-lean.md
Clone the repo
git clone --depth 1 https://github.com/tobiasosborne/alethfeld

Made for: Claude Code.

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 edn-to-lean

README.md
[![agentmods](https://agentmods.dev/badge/commands/tobiasosborne/alethfeld/edn-to-lean/github.svg)](https://agentmods.dev/commands/tobiasosborne/alethfeld/edn-to-lean)
Your own site
<a href="https://agentmods.dev/commands/tobiasosborne/alethfeld/edn-to-lean"><img src="https://agentmods.dev/badge/commands/tobiasosborne/alethfeld/edn-to-lean/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 edn-to-lean

Your own site · 80×15
<a href="https://agentmods.dev/commands/tobiasosborne/alethfeld/edn-to-lean"><img src="https://agentmods.dev/badge/commands/tobiasosborne/alethfeld/edn-to-lean.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 588 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00010 $0.00588
Opus 5 $0.00005 $0.00294
Sonnet 5 $0.00002 $0.00118
Haiku 4.5 $0.00001 $0.00059

Measured 12d ago against content hash bc58d6fd2245, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

edn-to-lean 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 12d 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/commands/edn-to-lean.md · 85 lines

What it actually says

EDN to Lean 4 Conversion

Convert an Alethfeld EDN proof to a Lean 4 formalization.

Input

User provides path to an EDN proof file.

Process

1. Parse EDN Structure

Read the EDN file and extract:

  • :theorem - the main claim
  • :symbols - type declarations
  • :assumptions - hypotheses
  • :steps - proof structure
  • :qed - final conclusion

2. Map to Lean Types

EDN Type Lean Type
Real or
Nat or
X → Y X → Y
Matrix m n R Matrix (Fin m) (Fin n) R
Operator H H →L[ℂ] H

3. Generate Lean Structure

import Mathlib
-- imports based on types used

namespace <ProofName>

-- Definitions from :definitions
def ... := ...

-- Main theorem from :theorem
theorem main_theorem
    (assumptions from :assumptions) :
    <theorem statement> := by
  -- tactics derived from :steps
  sorry -- initially, then fill in

4. Map Proof Steps to Tactics

EDN Justification Lean Tactic
:definition-expansion unfold, simp only [def]
:substitution rw, conv
:modus-ponens apply, exact
:algebraic-rewrite ring, field_simp
:case-split cases, rcases, by_cases
:induction-step induction
:contradiction by_contra, absurd
:admitted sorry

5. Output

Create the Lean file at lean/AlethfeldLean/<appropriate-path>.lean

Include:

  • Module docstring with theorem statement
  • All necessary imports
  • Type signatures matching EDN symbols
  • Proof skeleton with sorry where needed
  • Comments linking to EDN step IDs

6. Verify

cd lean && lake build <module-path>

Report any type errors and fix them before finishing.

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. 12d ago First seen · 85 lines · 10 tokens per session scan A bc58d6fd2245

Subscribe to this mod's changes

edn-to-lean is a command published in the GitHub repository tobiasosborne/alethfeld (144 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 588 once invoked, about $0.0001 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.