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.
npx agentmods add rules/verymath/co-mathematician/co-mathematician-rolesgit clone --depth 1 https://github.com/VeryMath/co-mathematicianWrote 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.
[](https://agentmods.dev/rules/verymath/co-mathematician/co-mathematician-roles)<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>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.
| Model | Per session | Once 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 |
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.
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.mdcomputational_experimenter:agents/roles/computational_experimenter.mdlogic_reviewer:agents/roles/logic_reviewer.mdadversarial_reviewer:agents/roles/adversarial_reviewer.mdcitation_checker:agents/roles/citation_checker.mdsynthesis_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.
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.
- 4d ago First seen · 34 lines · 303 tokens per session scan A a15691a1dead
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.
Other cursor rules, from other repositories
viash-component-authoring
Author or modify a Viash component (config.vsh.yaml + script) for an OpenProblems method, especially a taskistpreprocessing stage. Use when the user wants to add/implement a spatial method, scaffold a component, or fix a config.vsh.yaml.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.