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 skills add VeryMath/AI4Math-Writing --skill paper-writinggit clone --depth 1 https://github.com/VeryMath/AI4Math-WritingWrote 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/skills/verymath/ai4math-writing/paper-writing)<a href="https://agentmods.dev/skills/verymath/ai4math-writing/paper-writing"><img src="https://agentmods.dev/badge/skills/verymath/ai4math-writing/paper-writing.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 5.1 | $0.00040 | $0.01032 |
| Opus 5 | $0.00020 | $0.00516 |
| Sonnet 5 | $0.00008 | $0.00206 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
paper-writing 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 8d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Writing
Use this skill to help write mathematical papers from verified sources, notes, proof artifacts, experiment logs, or reviewer feedback. The workflow is for paper writing; unsupported-claim control is a required review step, not a separate public skill.
Use When
Use this skill when the user wants to:
- draft or revise a mathematical paper section;
- turn proof notes, experiment logs, or reading notes into paper text;
- prepare related work, positioning, abstracts, introductions, or conclusions;
- respond to reviewer comments with evidence-backed changes;
- audit a draft for unsupported claims, missing citations, unclear assumptions, or overstated contributions.
Do not use this skill to invent theorems, experiments, citations, author claims, or results that are not supported by the provided evidence.
Inputs
- Required: writing goal, target section or deliverable, and source materials.
- Optional: target venue, audience, style constraints, citation policy, reviewer comments, theorem/proof files, experiment logs, figures, or bibliography.
If source materials are missing, stop and ask for them or produce only an
explicit outline of needed evidence. For recurring work, start from
templates/source-packet.md.
Outputs
- Draft or revised paper text.
- Claim-evidence notes for substantive mathematical, empirical, or literature claims.
- A list of unsupported, uncertain, or citation-needed statements.
- Suggested next edits and required source checks.
Subskill Routing
Read skills/registry.yaml when the task needs a specialized audit.
| Need | Subskill |
|---|---|
| Build a rapid paper skeleton, section plan, or result dependency map before prose | paper-skeleton-and-logical-architecture |
| Map claims to proofs, citations, experiments, or uncertainty | claim-evidence-ledger |
| Audit theorem assumptions, proof obligations, edge cases, or external theorem fit | proof-obligation-and-assumption-audit |
| Check notation drift, variable reuse, symbol scope, domains, or dimensions | notation-and-variable-consistency |
| Improve displayed formulas, derivations, theorem/proof environments, and formula prose | formula-environment-and-readability |
| Check LaTeX builds, labels, references, citations, macros, floats, layout warnings, and submission preflight risks | latex-build-and-layout-audit |
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- README.md 3.9 KB
- README.zh-CN.md 3.5 KB
- skills/claim-evidence-ledger/SKILL.md 2.2 KB
- skills/formula-environment-and-readability/SKILL.md 1.6 KB
- skills/latex-build-and-layout-audit/SKILL.md 3.5 KB
- skills/notation-and-variable-consistency/SKILL.md 1.6 KB
- skills/paper-skeleton-and-logical-architecture/SKILL.md 2.4 KB
- skills/proof-obligation-and-assumption-audit/SKILL.md 2.5 KB
- skills/registry.yaml 1.2 KB
- templates/claim-evidence-ledger.md 889 B
- templates/proof-obligation-ledger.md 993 B
- templates/rapid-prototype-paper-skeleton.md 1.3 KB
- templates/source-packet.md 1.1 KB
- templates/submission-readiness.md 1.2 KB
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.
- 8d ago First seen · 106 lines · 40 tokens per session scan A 08a4b0d688e1
paper-writing is a skill published in the GitHub repository VeryMath/AI4Math-Writing (6 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,032 once invoked, about $0.0002 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 skills, from other repositories
or-solver
Unified solver detection, installation, selection, and license configuration for OR optimization skills (LP, MIP, SOCP). One-stop solver management: detect installed packages, install missing solvers with proper priority, select the best available solver by problem type, and troubleshoot common errors. Covers 20…
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…
linear-programming
Models and solves linear programs (LP) with multiple solvers (COPT, Gurobi, MOSEK, CPLEX, HiGHS (scipy/highspy), CLARABEL, PuLP/CBC, CVXOPT, OR-Tools/GLOP, GLPK, SoPlex, lpsolve, ECOS). Restates natural-language word problems into LP before building and solving. When no local solver is available, searches GitHub for…
copt-linear-program
A tool for turning linear programming problems into mathematical models and solving them with Cardinal Optimizer, a software package for optimization. It can start from a word problem or from supplied matrices and JSON data.
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…
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…