co-mathematician-roles

co-mathematician-roles is a cursor rule for Cursor from VeryMath/co-mathematician. It costs 303 tokens per session, scanned A, original, MIT.

A set of rules that adapts defined mathematics research roles for Cursor Agent, an AI coding assistant. It directs the agent to use role instructions, record work, and keep evidence and uncertainty clear.

In plain words
What is it for?
Use it to run focused proof exploration, computation, logic review, adversarial review, citation checking, and research synthesis within an assigned workstream.
Why use it?
It prevents research tasks from drifting, losing their supporting work, or being approved by the same agent that produced them.

Cursor rule for Cursor

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 rules/verymath/co-mathematician/co-mathematician-roles
Clone the repo
git clone --depth 1 https://github.com/VeryMath/co-mathematician

Made for: Cursor.

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 co-mathematician-roles

README.md
[![agentmods](https://agentmods.dev/badge/rules/verymath/co-mathematician/co-mathematician-roles.svg)](https://agentmods.dev/rules/verymath/co-mathematician/co-mathematician-roles)
Your own site
<a href="https://agentmods.dev/rules/verymath/co-mathematician/co-mathematician-roles"><img src="https://agentmods.dev/badge/rules/verymath/co-mathematician/co-mathematician-roles.svg" alt="Measured on agentmods" height="20"></a>
Per session 303 This file is loaded in full into every session.
When invoked 303 The same file — it is already loaded in full.
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 $0.00303 $0.00303
Opus 5 $0.00151 $0.00151
Sonnet 5 $0.00061 $0.00061
Haiku 4.5 $0.00030 $0.00030

Measured 4d ago against content hash a15691a1dead, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

co-mathematician-roles 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 4d 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.

.cursor/rules/co-mathematician-roles.mdc · 34 lines

What it actually says

Co-Mathematician Role Adapter

Cursor does not use .codex/agents/*.toml or .claude/agents/*.md as native agent definitions. Treat agents/roles/ as the canonical role layer and use Cursor Agent sessions, focused chats, or fresh reviewer prompts as the adapter.

Canonical role cards:

  • proof_explorer: agents/roles/proof_explorer.md
  • computational_experimenter: agents/roles/computational_experimenter.md
  • logic_reviewer: agents/roles/logic_reviewer.md
  • adversarial_reviewer: agents/roles/adversarial_reviewer.md
  • citation_checker: agents/roles/citation_checker.md
  • synthesis_agent: agents/roles/synthesis_agent.md

When asked to perform one of these roles:

  • Read the matching canonical role card before acting.
  • Work only on the approved goal or workstream supplied by the Project Coordinator.
  • Save artifacts, failed explorations, reviews, and reports in the workstream directory.
  • Keep provenance and uncertainty explicit.
  • Do not start new goals or workstreams.
  • Do not mark any workstream complete.
  • Do not self-approve your own report.
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. 4d ago First seen · 34 lines · 303 tokens per session scan A a15691a1dead

Subscribe to this mod's changes

co-mathematician-roles is a cursor rule published in the GitHub repository VeryMath/co-mathematician (7 stars, last pushed 6d ago), licensed MIT. It adds 303 tokens to every session, about $0.0015 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 2026-08-31.