decompose-proof

A command that breaks long Lean mathematical proofs into smaller helper lemmas, which are reusable intermediate statements.

In plain words
What is it for?
Use it on a long proof or theorem. It first plans the mathematical split, then creates helpers, checks for duplicates, and verifies the final arrangement.
Why use it?
Shorter proofs are easier to read, check, maintain, and reuse than one long proof containing every step.

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/decompose-proof
Clone the repo
git clone --depth 1 https://github.com/CBirkbeck/mathlib-quality
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,527 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 $0.00011 $0.05527
Opus 5 $0.00005 $0.02763
Sonnet 5 $0.00002 $0.01105
Haiku 4.5 $0.00001 $0.00553

Measured 2d ago against content hash 60d3ff87a85c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

decompose-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 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/decompose-proof.md · 587 lines

How it starts

The opening of the file, as written. The whole thing — 587 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/decompose-proof - Two-Pass Proof Decomposition

CRITICAL: No proof should exceed 50 lines. Target: main theorems <15 lines.

Break long proofs into helper lemmas by understanding the mathematical structure first, then implementing.

Usage

/decompose-proof [file_path]
/decompose-proof [theorem_name]

If no argument, operates on the currently open file.

Architecture

Problem: Agents rush into decomposition without fully understanding the proof. They miss mathlib lemmas, create single-use helpers with bad names, and forget to consolidate.

Solution: Separate analysis from implementation:

  1. Pass 1 (Analysis): Identify ALL proofs needing decomposition. For each, study the mathematics and write a detailed decomposition plan as a comment block above the proof.
  2. Pass 2 (Decompose): Dispatch parallel agents, each handling one proof. They study the proof, search mathlib, then implement the plan.
  3. Pass 3 (Consolidate): Review all new helpers for duplicates and shared patterns.

Pass 1: Analysis

Step 1: Identify Candidates

Read the entire file and build a table of ALL proofs by length:

## Proof Length Report

| Declaration | Lines | Action |
|-------------|-------|--------|
| `main_theorem` | 65 | CRITICAL (>50) — aggressive decomposition |
| `helper_result` | 38 | MUST decompose (>30) |
| `medium_proof` | 22 | CONSIDER decomposition (15-30) |
| `small_lemma` | 12 | OK |

Also flag structural issues regardless of length:

  • in theorem statement → MUST split
  • constructor with any branch >10 lines → MUST extract branches
  • by_cases/rcases/match/induction with any branch >10 lines → MUST extract branches
  • set_option maxHeartbeats → MUST decompose (remove the set_option)

Step 2: Study Each Candidate

For EACH proof flagged for decomposition, read it carefully before writing any plan. Answer these questions (write answers in your reasoning, not in the file):

  1. What is the theorem proving? (plain language, 1-2 sentences)
  2. What are the key mathematical steps? (3-5 bullet points, using math language like "establish bound", "show convergence", NOT "apply lemma X")
  3. What independent facts are being established? (each is a candidate helper)
  4. What estimates/bounds appear? (have h : ‖...‖ ≤ ... blocks are extraction candidates)
  5. Are there cases/branches >10 lines? (mandatory extraction)
  6. Are there repeated patterns across proofs? (consolidation candidates)

Read the full file on GitHub · 587 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 · 587 lines · 11 tokens per session scan A 60d3ff87a85c

Subscribe to this mod's changes

decompose-proof is a command published in the GitHub repository CBirkbeck/mathlib-quality (32 stars, last pushed 13d ago), licensed MIT. It adds 11 tokens to every session and 5,527 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.