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 instructions/verymath/co-mathematician/claude-mdgit 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/instructions/verymath/co-mathematician/claude-md)<a href="https://agentmods.dev/instructions/verymath/co-mathematician/claude-md"><img src="https://agentmods.dev/badge/instructions/verymath/co-mathematician/claude-md.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 | $0.00902 | $0.00902 |
| Opus 5 | $0.00451 | $0.00451 |
| Sonnet 5 | $0.00180 | $0.00180 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
co-mathematician CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Repository Contract
This repository is a coding-agent-driven AI Co-Mathematician workspace.
When Claude Code is operating in this repository:
- The main Claude Code conversation is the Project Coordinator.
- The repository filesystem is the shared artifact store.
agents/roles/is the canonical role layer..claude/agents/contains Claude Code adapters for the canonical roles.- Task agents or clearly separated reviewer passes are workstream coordinators, specialized agents, and reviewers.
- The harness only provides state files, gates, report skeletons, and checks.
- Do not build a new multi-agent platform here.
- Do not start a mathematical research project during workspace initialization.
Required Flow
Default workspace mode:
onboarding -> research question formalization -> goal approval -> workstreams -> reviewer loop -> final working paper
If the user explicitly invokes a project-local domain Skill, or accepts a Skill
suggested by co-math suggest-skills, enter skill-guided mode instead. Record
the handoff with co-math skill-handoff and follow that Skill's own opening,
modeling, and approval flow for the inner task. Promote the task into goals and
workstreams only when the user wants durable research output, reviewer-gated
claims, or a final working paper.
Hard rules:
- Default workspace mode runs onboarding before goal approval.
- During workspace-mode onboarding, ask the user to choose a workspace document language policy.
- Refresh the project-local skill registry at session start, after skill installation, and before formalizing goals.
- Before creating any workstream, match the workstream scope against the project-local skill registry and read any relevant
SKILL.md. - Always get explicit user approval of goals before starting any workstream.
- Never start a workstream for an unapproved goal.
- Important claims must include provenance.
- Failed explorations must be saved as durable artifacts.
- Uncertainty must be exposed explicitly in reports and status updates.
- Every workstream report must be reviewed by an independent reviewer pass or agent.
- A workstream whose review has not passed must not be marked complete.
- Final output must be a working paper, not a chat summary.
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.
- 3d ago First seen · 77 lines · 902 tokens per session scan A c393b66c736f
co-mathematician CLAUDE.md is an instructions file published in the GitHub repository VeryMath/co-mathematician (7 stars, last pushed 5d ago), licensed MIT. It adds 902 tokens to every session, about $0.0045 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 instructions, from other repositories
Danus AGENTS.md
Instructions for frenzymath/Danus, covering danus — codex main-agent contract, role, two exploration lanes, continuous parallel mathematical reasoning and persistent goal and timed strategy loop.
SutroYaro GEMINI.md
Instructions for cybertronai/SutroYaro, covering gemini.md - sutro group research workspace, project context, read these first, core concepts and current best methods.
SutroYaro AGENTS.md
Instructions for cybertronai/SutroYaro, covering agents.md, for single agents (getting started), how ai agents were used, for agents reviewing prs and for agents running experiments.
math-anchor AGENTS.md
AGENTS.md instructions for tetracoralla/math-anchor: Read docs/product-model.md and docs/REVIEWCONTRACT.md before changing or reviewing the product surface.
reaper CLAUDE.md
Instructions for SebastianElvis/reaper, covering reaper, project structure, commands, run tests (includes l1 structural eval graders) and run the layered evals.
math-anchor CLAUDE.md
Claude Code instructions for tetracoralla/math-anchor, a project described as: Math Anchor — safe exact and scientific math, units, and dimensional analysis for humans and Agents (macOS + MCP/Codex plugin).