autoprove

autoprove is a command for Claude Code, Codex from cameronfreer/lean4-skills. It costs 14 tokens per session (4,471 once invoked), scanned A, original, MIT.

An automatic Lean 4 proof runner that repeats proof attempts in cycles until it reaches a stopping limit or finishes. Lean 4 is a programming language and proof checker for formal mathematics.

In plain words
What is it for?
Use it on a project or file, set a maximum number of cycles, or restrict it to repairing build errors without filling unfinished proofs.
Why use it?
It handles repeated proving and repair steps without requiring a person to start each cycle. Explicit limits prevent an open-ended run.

Command for Claude CodeCodex

Written for Claude Code and Codex: user-invocable in frontmatter, but also runs codex exec. Also seen: mentions subagents; mentions Codex.

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

Good fit Use it on a project or file, set a maximum number of cycles, or restrict it to repairing build errors without filling unfinished proofs.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/cameronfreer/lean4-skills/autoprove
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.

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

Made for: Claude Code, Codex.

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

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 autoprove

README.md
[![agentmods](https://agentmods.dev/badge/commands/cameronfreer/lean4-skills/autoprove.svg)](https://agentmods.dev/commands/cameronfreer/lean4-skills/autoprove)
Your own site
<a href="https://agentmods.dev/commands/cameronfreer/lean4-skills/autoprove"><img src="https://agentmods.dev/badge/commands/cameronfreer/lean4-skills/autoprove.svg" alt="Measured on agentmods" height="20"></a>
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 4,471 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 $0.00014 $0.04471
Opus 5 $0.00007 $0.02235
Sonnet 5 $0.00003 $0.00894
Haiku 4.5 $0.00001 $0.00447

Measured 3d ago against content hash e5497eb98231, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

autoprove 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/autoprove.md · 294 lines

How it starts

The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lean4 Autoprove

Autonomous multi-cycle theorem proving. Runs cycles automatically with explicit stop budgets and structured summaries.

Usage

/lean4:autoprove                        # Start autonomous session
/lean4:autoprove File.lean              # Focus on specific file
/lean4:autoprove --repair-only          # Fix build errors without filling sorries
/lean4:autoprove --max-cycles=10        # Limit total cycles

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 Phase 1.

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. Call lean4-skills-cycle-tracker init with resolved numeric values for --max-cycles, --max-stuck-cycles, --max-total-runtime, --max-deep-per-cycle, and --max-consecutive-deep-cycles. A failed init (exit 2) is a startup validation error — do not proceed.
  4. The state file is the single source of truth for session counters. Read counters from tick/status output, not from conversational memory.

Inputs

Arg Required Default Description
scope No all Specific file or theorem to focus on
--repair-only No false Fix build errors only, skip sorry-filling
--planning No on on or off
--review-source No internal internal, external, both, or none (see coercion below)
--review-every No checkpoint N (sorries), checkpoint, or never
--checkpoint No true Create checkpoint commits after each cycle
--deep No stuck never, stuck, or always (ask coerced to stuck — see Deep Mode)
--deep-sorry-budget No 2 Max sorries per deep invocation
--deep-time-budget No 20m Advisory: scopes deep-mode subagent work. Not tracked or enforced by session tracker.
--max-deep-per-cycle No 1 Max deep invocations per cycle
--max-consecutive-deep-cycles No 2 Hard cap on consecutive cycles using deep mode
--deep-snapshot No stash V1: stash only
--deep-rollback No on-regression on-regression, on-no-improvement, always, or never (see coercion below)
--deep-scope No target target or cross-file
--deep-max-files No 2 Max files per deep invocation
--deep-max-lines No 200 Max added+deleted lines per deep invocation
--deep-regression-gate No strict strict or off (see coercion below)
--batch-size No 2 Sorries to attempt per cycle (advisory)
--commit No auto auto or never (ask coerced to auto — see note below)
--golf No never prompt, auto, or never
--max-cycles No 20 Session stop budget: max total cycles
--max-total-runtime No 120m Best-effort wall-clock session budget
--max-stuck-cycles No 3 Session stop budget: max consecutive stuck cycles
--formalize No never never | restage | auto. See Formalize Outer Loop. (deprecated: use /lean4:autoformalize)
--source No File path, URL, or PDF for claim extraction. Required when --formalize=auto. (deprecated: use /lean4:autoformalize)
--claim-select No first | named:"..." | regex:"...". Queue-extraction filter applied once at startup. Required when --formalize=auto. Ignored without --source. (deprecated: use /lean4:autoformalize)
--formalize-rigor No sketch sketch | checked. Rigor for formalize skeleton. (deprecated: use /lean4:autoformalize --rigor)
--statement-policy No preserve preserve | rewrite-generated-only | adjacent-drafts. Default becomes rewrite-generated-only when --formalize=restage|auto (see flag validation). (deprecated: use /lean4:autoformalize)
--formalize-out No Target file for formalized claims. Required if no existing target in scope. (deprecated: use /lean4:autoformalize --out)

Read the full file on GitHub · 294 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 Changed · +10 lines e5497eb98231
  2. 8d ago First seen · 284 lines · 14 tokens per session scan A 400f83b8c5ab

Subscribe to this mod's changes

autoprove is a command published in the GitHub repository cameronfreer/lean4-skills (432 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 4,471 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.