agentmods.dev

co-mathematician

co-mathematician is a skill for Claude Code, Codex from VeryMath/co-mathematician. It costs 26 tokens per session (502 once invoked), scanned A, original, MIT.

A project-management workflow for carrying out one defined piece of software work from its requirements through implementation. It sends the work to a delivery lead, who coordinates developers, dependencies, and the test plan.

In plain words
What is it for?
Use it to select a roadmap slice, confirm its size and dependencies, create an implementation packet and task list, and run the required delivery workflow.
Why use it?
Large projects are easier to deliver when work is split into manageable slices with clear acceptance criteria. This process prevents an oversized slice from being started without first breaking it down.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

not rated 9repo today A scan 26 tokens original MIT

Good fit Use it to select a roadmap slice, confirm its size and dependencies, create an implementation packet and task list, and run the required delivery workflow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/verymath/co-mathematician/co_mathematician
View source ↗ VeryMath/co-mathematician
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.

Any agent
npx skills add VeryMath/co-mathematician --skill co_mathematician
Clone the repo
git clone --depth 1 https://github.com/VeryMath/co-mathematician

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/verymath/co-mathematician/co_mathematician/github.svg)](https://agentmods.dev/skills/verymath/co-mathematician/co_mathematician)
Your own site
<a href="https://agentmods.dev/skills/verymath/co-mathematician/co_mathematician"><img src="https://agentmods.dev/badge/skills/verymath/co-mathematician/co_mathematician/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for co-mathematician

Your own site · 80×15
<a href="https://agentmods.dev/skills/verymath/co-mathematician/co_mathematician"><img src="https://agentmods.dev/badge/skills/verymath/co-mathematician/co_mathematician.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 502 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 $0.00026 $0.00502
Opus 5.5 $0.00010 $0.00201
Sonnet 5 $0.00005 $0.00100
Haiku 4.5 $0.00003 $0.00050

Measured today against content hash c87300b53d46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-27, from the pricing page.

Security

Grade A, and why

co-mathematician 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 today.

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.

harness/co_math/resources/co_mathematician_skill.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Co-Mathematician

Use the repository files as durable project memory. The active coding-agent conversation coordinates the work; co-math only manages project files and reports their current state.

Project Lifecycle

  • Create a project with co-math new "<name>". Return the new path and ask the user to open that directory. Do not start the research in the creation conversation.
  • Use co-math list to find existing projects.
  • At the start of a project session, run co-math resume --project ..
  • When unsure what to do, run co-math next --project . and take only the next useful action.
  • Ask the user to confirm before archiving finished work with co-math archive --project .. Archiving never deletes research files. Use co-math reopen --project . to continue later.

Keep replies short: current situation, first blocker if any, and one next action.

Research Workflow

  1. Read AGENTS.md and the current files under workspace/project/.
  2. During onboarding, ask the user to choose the document language and clarify the research question. Do not solve the problem yet.
  3. Check .agents/skills/ for a relevant mathematical domain Skill. If one is selected, follow its inner workflow.
  4. Record the research question and draft goals in workspace/project/GOALS.yaml.
  5. Start a workstream only after the user explicitly approves its goal.
  6. Save proof attempts, computations, literature notes, failed routes, and uncertainty in the workstream directory.
  7. Ask an independent reviewer to inspect every completed workstream report. The report author cannot approve their own report.
  8. Produce workspace/final/working_paper.md as the final research output, not a chat summary.

Durable Files

workspace/project/       question, goals, status, messages
workspace/workstreams/   proofs, computations, literature, failures, reviews
workspace/final/         final working paper

Important claims must point to user input, literature, a proof, a computation, or a review. Keep failed attempts and unresolved uncertainty visible.

Read the full file on GitHub · 54 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. today First seen · 54 lines · 26 tokens per session scan A c87300b53d46

Subscribe to this mod's changes

co-mathematician is a skill published in the GitHub repository VeryMath/co-mathematician (9 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 502 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-27.

PlanningProject managementai-researchai4mathco-mathematicianmathematics
Related

Other skills, from other repositories

ara-research-manager

Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during…

Orchestra-Research/AI-Research-SKILLs · 91 tokens

cdopt-optimization

Use when Codex needs to solve, reproduce, test, compare, generate examples for, or diagnose CDOpt manifold optimization workflows, including CDOpt package smoke tests, official problem description cards, Stiefel dictionary learning, SciPy wrappers, PyTorch/JAX/NumPy CDOpt examples, dependency checks, tiny CPU…

VeryMath/AI4Math-Optimization · 80 tokens

osqp-solver

Model, solve, update, reproduce, and diagnose continuous convex quadratic programs with the OSQP Python interface, including canonical-form conversion, sparse CSC data, solver-status gates, residual checks, infeasibility certificates, warm starts, repeated parametric QPs, and academic citation. Use when a task names…

VeryMath/AI4Math-Optimization · 131 tokens

second-order-cone-programming

Models and solves second-order cone programs and problems convertible to SOCP form using cvxpy with multiple solver backends (COPT, Gurobi, MOSEK, CPLEX, CLARABEL, ECOS, SCS, CVXOPT, COSMO, OSQP). Handles linear objectives with second-order cone constraints, as well as problems reducible to SOCP such as portfolio…

VeryMath/AI4Math-Optimization · 114 tokens

mixed-integer-programming

Models and solves mixed-integer linear programs, including binary, integer, and continuous decision variables with linear objectives and constraints.

VeryMath/AI4Math-Optimization · 30 tokens

or-solver

Configure the Python environment for a solver already specified by the user or a modeling skill. Check the target interpreter and dependencies, install required packages, configure licenses and environment variables, troubleshoot setup errors, and report availability. Use for installing or repairing a named solver…

VeryMath/AI4Math-Optimization · 69 tokens