draft

A command that turns an informal mathematical claim into a Lean 4 declaration skeleton with unfinished proof placeholders. Lean 4 is a language and checker for machine-verified mathematics.

In plain words
What is it for?
Use it to draft theorem statements from text, claims in a PDF, or a named result, then pass the generated file to a proving command.
Why use it?
It provides a structured starting point when you know what should be true but have not yet written the formal statement or proof.

Command

Part of the lean4 plugin — 1 skill, 12 commands, 4 agents, 3 hooks shipped together

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/cameronfreer/lean4-skills/draft
Clone the repo
git clone --depth 1 https://github.com/cameronfreer/lean4-skills

Or install lean4, the plugin that ships this one along with the rest of its 1 skill, 12 commands, 4 agents, 3 hooks.

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 3,439 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 $0.00010 $0.03439
Opus 5 $0.00005 $0.01720
Sonnet 5 $0.00002 $0.00688
Haiku 4.5 $0.00001 $0.00344

Measured 3d ago against content hash 9055456f569e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

draft 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 3d 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.

plugins/lean4/commands/draft.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lean4 Draft

Draft Lean 4 declaration skeletons from informal mathematical claims. Produces sorry-stubbed statements ready for /lean4:prove or /lean4:autoprove.

Usage

/lean4:draft "Every continuous function on a compact set is bounded"
/lean4:draft --mode=attempt "Zorn's lemma implies AC"
/lean4:draft --source ./paper.pdf          # Ingest, pick claims, draft skeletons
/lean4:draft --source ./paper.pdf "Theorem 3.2"  # Source as context, topic as claim
/lean4:draft --output=file --out=MyTheorem.lean "..."

Invocation Contract

Interpret this command's inputs per the Command Invocation Contract.

Primary path (hook-validated): If a validated-invocation block for this command appears in context, treat it as the authoritative interpretation of parser-decidable inputs and do not re-parse the raw invocation text for those inputs. Start by reading all parser-decided fields from the block. Emit the final Resolved Inputs summary from the block values. See Validated Invocation Block.

Fallback path (other hosts): If no validated-invocation block is present, parse the raw invocation text against this command's input table before claim acquisition.

Startup requirements:

  1. Emit a Resolved Inputs block with explicit values, defaults, coercions, ignored flags, and startup validation errors.
  2. Refuse to start on startup validation errors.
  3. Validate output paths and overwrite policy before writing anything.

Inputs

Arg Required Default Description
topic no Informal claim to draft. Optional when --source provides it (source-led flow). At least one of topic or --source must be given; omitting both is a startup validation error.
--mode no skeleton skeleton | attempt. skeleton produces sorry-stubbed declarations only. attempt adds a proof-attempt loop (lean_multi_attempt) before finalizing.
--elab-check no best-effort best-effort | strict. Elaboration check strictness for drafted skeletons.
--level no intermediate beginner | intermediate | expert
--output no chat chat | scratch | file
--out no Output path. Required when --output=file; startup validation error if missing.
--overwrite no false Allow overwriting existing files with --output=file. Without flag, existing target → startup validation error.
--mathlib-template no false Emit the mathlib module-system file header on --output=file writes regardless of detected project context. Requires --output=file; mutually exclusive with --no-mathlib-template.
--no-mathlib-template no false Never emit the mathlib module-system file header on --output=file writes, regardless of detected project context. Requires --output=file; mutually exclusive with --mathlib-template.
--source no File path, URL, or PDF to seed drafting. See learn-pathways.md.
--intent no math auto | usage | math. See learn-pathways.md.
--presentation no auto informal | supporting | formal | auto. Controls user-facing display, not Lean backing. See learn-pathways.md.
--claim-select no first | named:"..." | regex:"...". Noninteractive claim selection from --source. See below.

Read the full file on GitHub · 166 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. 3d ago First seen · 166 lines · 10 tokens per session scan A 9055456f569e

Subscribe to this mod's changes

draft is a command published in the GitHub repository cameronfreer/lean4-skills (418 stars, last pushed 7d ago), licensed MIT. It adds 10 tokens to every session and 3,439 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.