autoprove

autoprove is a command for Claude Code, Codex from frenzymath/Archon. It costs 14 tokens per session (3,590 once invoked), scanned A, original, Apache-2.0.

A command that repeatedly tries to prove Lean 4 theorems and repair build errors. Lean 4 is a language for writing machine-checked mathematical proofs.

In plain words
What is it for?
Use it across a project or selected file, to fill sorries, repair build errors only, run planning and reviews, and create checkpoint commits between cycles.
Why use it?
It automates repeated proof attempts while applying limits and stopping rules so an unsuccessful theorem does not run indefinitely.

Command for Claude CodeCodex

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

Part of the lean4 plugin — 1 skill, 11 commands, 4 agents, 3 hooks shipped together

Good fit Use it across a project or selected file, to fill sorries, repair…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/frenzymath/archon/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/frenzymath/Archon

Made for: Claude Code, Codex.

Or install lean4, the plugin that ships this one along with the rest of its 1 skill, 11 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/frenzymath/archon/autoprove.svg)](https://agentmods.dev/commands/frenzymath/archon/autoprove)
Your own site
<a href="https://agentmods.dev/commands/frenzymath/archon/autoprove"><img src="https://agentmods.dev/badge/commands/frenzymath/archon/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 3,590 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 $0.03590
Opus 5 $0.00007 $0.01795
Sonnet 5 $0.00003 $0.00718
Haiku 4.5 $0.00001 $0.00359

Measured 7d ago against content hash 17104dae029e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 7d 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.

src/archon/.archon-src/skills/lean4/commands/autoprove.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 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 hard stop conditions 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

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 Max time per deep invocation
--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
--commit No auto auto or never (ask coerced to auto — see note below)
--golf No never prompt, auto, or never
--max-cycles No 20 Hard stop: max total cycles
--max-total-runtime No 120m Hard stop: max total runtime
--max-stuck-cycles No 3 Hard stop: 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 · 241 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. 7d ago First seen · 241 lines · 14 tokens per session scan A 17104dae029e

Subscribe to this mod's changes

autoprove is a command published in the GitHub repository frenzymath/Archon (215 stars, last pushed 20d ago), licensed Apache-2.0. It adds 14 tokens to every session and 3,590 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.

Related

Other commands, from other repositories

protocol-check

Validate a patient's triage categorization against START, JumpSTART, SALT, or ESI protocol criteria. Provides immediate feedback and protocol citations.

DaxxSec/cognitropy-lab · 0 tokens

crash-kinematics

Apply automotive crash test interpretation methodology — delta-V, kinetic-energy partitioning, IIHS / Euro NCAP cabin-intrusion bands — to a credible vehicle-borne attack scenario. The output gives the threat-assessment its impact score for any vehicle-borne row, replacing qualitative guesswork with computed bands.

DaxxSec/cognitropy-lab · 0 tokens

fitting-gauge-rr

Run a Gauge R&R (Repeatability & Reproducibility) study on a measurement system used in the practice — caliper, 3D socket scanner, pressure mat, force plate, motion capture. Reports % R&R and % contribution per the AIGM MSA Manual.

DaxxSec/cognitropy-lab · 0 tokens

gait-asymmetry-detect

Statistically detect prosthetic-vs-sound-side gait asymmetry beyond known-population baselines — paired-sample inference with effect size.

DaxxSec/cognitropy-lab · 0 tokens

gait-lab-spc-baseline

Establish Statistical Process Control baselines from a patient's gait-lab kinematic and kinetic data — locks the in-control distribution that all subsequent visits' control charts will reference.

DaxxSec/cognitropy-lab · 0 tokens

proms-trend-analysis

Statistical trend analysis on patient-reported outcome measures (PEQ, AMP-PRO, PROMIS-PF, Houghton Scale of Use) across encounters — reports trends with within-subject SEM and against published MCID thresholds.

DaxxSec/cognitropy-lab · 0 tokens