Math Proof

math-proof

Two Claude Code skills for hard, research-level mathematics problems. Each takes one problem stated in full, keeps everything it writes in a run folder, switches Claude Code's web tools off for its run, and ends with a self-contained proof.md.

/math-proof:solo: Claude works the problem itself, in your session, as one long turn. It is instructed to write its plan and each intermediate result to a notes file before reasoning further, so that a response cut off at the output limit loses nothing already written. The lighter of the two; try it first.

/math-proof:siege (multi-agent): your session does no mathematics itself; for hours it runs rounds of sub-agents, each starting fresh. Each round a judge writes a few self-contained questions, independent workers answer them in parallel, and the judge keeps a ledger of what is proved, refuted and open. When a worker's answer contains a complete proof (or disproof) of the goal the judge set, two more workers check that exact text line by line before the judge concludes; if the opening rounds do not get there, later rounds send more workers per round, most of them at the one step the proof still lacks. proof.md has a Status section saying plainly what is and is not proved. Expect dozens of sub-agent runs, and well over a hundred if all fourteen rounds run: check /usage before you start on a subscription, or cap the spend with --max-budget-usd in the unattended form below on an API key.

Either way proof.md is the model's own account, and any result it cites from the literature is quoted from memory: read it critically. Full instructions: skills/solo/SKILL.md and skills/siege/SKILL.md; the sub-agents are defined in agents/.

Install

/plugin install math-proof@claude-plugins-official

Needs Claude Code 2.1.280 or later and, for siege, Python 3.7 or later on your PATH as python3 or python (no extra packages). Then add this "env" block once to ~/.claude/settings.json (or to .claude/settings.json in the directory you run from, to limit it to that directory). The three lines allow long responses, keep sub-agents in the foreground by turning background tasks off, and give a silent worker four hours before it is cut off; they affect every session that reads the file, so remove them when you stop using the plugin.