split-file

A command that breaks a large Lean file into smaller modules grouped around related definitions and theorems.

In plain words
What is it for?
Use it to analyse a large file and create a focused multi-file structure such as definitions, basic lemmas, and main theorems.
Why use it?
It makes files easier to navigate and maintain when they have grown beyond about 1,500 lines.

Command

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 commands/cbirkbeck/mathlib-quality/split-file
Clone the repo
git clone --depth 1 https://github.com/CBirkbeck/mathlib-quality
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,658 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 $0.00014 $0.01658
Opus 5 $0.00007 $0.00829
Sonnet 5 $0.00003 $0.00332
Haiku 4.5 $0.00001 $0.00166

Measured 2d ago against content hash 95da4978f7a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

split-file 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.

commands/split-file.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/split-file - Split Large Lean Files

Split a large Lean file (>1500 lines) into smaller, focused modules.

Usage

/split-file [file_path]

Splitting Strategy

Step 1: Analyze the File

  1. Get the file outline using lean_file_outline
  2. List all declarations with their line numbers
  3. Group declarations by naming prefix (e.g., cauchyPrincipalValue*, residue*)

Step 2: Identify Natural Groupings

Group declarations by the object they work on, identified by naming patterns:

Prefix Pattern Suggested File
cauchyPrincipalValue* CauchyPrincipalValue.lean
residue*, Residue* Residue.lean
pv_*, PV* PrincipalValue.lean
winding*, Winding* WindingNumber.lean
integral_* Integration.lean
Core definitions Basic.lean or Defs.lean

Step 3: Determine Split Structure

Option A: Two-file split (for 1500-3000 lines)

Module/
├── Basic.lean      -- Core definitions + simple lemmas
└── Theorems.lean   -- Main results (imports Basic)

Option B: Multi-file split (for >3000 lines)

Module/
├── Defs.lean       -- Core definitions only
├── Basic.lean      -- API lemmas (imports Defs)
├── Topic1.lean     -- Grouped lemmas (imports Basic)
├── Topic2.lean     -- Grouped lemmas (imports Basic)
└── Main.lean       -- Main theorems (imports all above)

Step 4: Execute the Split

For each new file:

  1. Create the file with proper header:
/-
Copyright (c) 2024 [Author]. All rights reserved.
Released under Apache 2.0 license as described in the file LICENSE.
Authors: [Author]
-/
import [necessary imports]

/-!
# [Module Title]

[Brief description]

## Main definitions/results

* `foo`: Description
-/
  1. Move declarations preserving order (dependencies must come before dependents)

  2. Update imports in all affected files

  3. Verify each file compiles before proceeding to next

Step 5: Verify

  1. Run lake build on each new file
  2. Ensure no circular imports
  3. Check that downstream files still compile

Read the full file on GitHub · 213 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 · 213 lines · 14 tokens per session scan A 95da4978f7a1

Subscribe to this mod's changes

split-file is a command published in the GitHub repository CBirkbeck/mathlib-quality (32 stars, last pushed 13d ago), licensed MIT. It adds 14 tokens to every session and 1,658 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.