A guide to clear mathematical writing, including explanations, proofs, notation, LaTeX, and docstrings. It is based on advice from established mathematics and technical-writing references.

Writing or editing mathematical prose in papers, documentation, LaTeX, Markdown, plain text, and code comments.

It helps make mathematical ideas easier to follow by keeping symbols, definitions, and proof steps consistent.

write-math — Skill for Claude Code by cboone/agent-harness-plugins

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 cboone/agent-harness-plugins --skill write-math

Clone the repo

git clone --depth 1 https://github.com/cboone/agent-harness-plugins

Made for: Claude Code.

Or install write-math, the plugin that ships this one along with the rest of its 1 skill.

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.

$agentmods badge for write-math$

README.md

[![agentmods](https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/write-math/github.svg)](https://agentmods.dev/skills/cboone/agent-harness-plugins/write-math)

Your own site

<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/write-math"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/write-math/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.

$agentmods 80×15 button for write-math$

Your own site · 80×15

<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/write-math"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/write-math.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 761 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.

Model	Per session	Once invoked
Fable 5.1	$0.00041	$0.00761
Opus 5.5	$0.00016	$0.00304
Sonnet 5.5	$0.00008	$0.00152
Haiku 4.5	$0.00004	$0.00076

Measured 8d ago against content hash 97a82e00430b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

write-math 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.

plugins/write-math/skills/write-math/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Math

Apply the mathematical writing conventions from the reference files below when drafting or editing mathematical content in any format.

Core Principles

Clarity over cleverness -- write so a graduate student beginning studies in the field can follow your argument
Reader-centered exposition -- minimize the reader's effort at every turn; signal where you are going and why
Consistent notation -- define symbols before use, reuse the same letter for the same concept, and never overload
Structured proofs -- state the theorem first, summarize the proof strategy, then present the formal argument in linear forward flow
Communication over impression -- plain language beats jargon; repetition beats synonym-hunting

Workflow

Review against the essential checklist: ./references/essential/checklist.md
For specific questions, consult the comprehensive references below

Quick reviews (default):

references/essential/checklist.md -- condensed, actionable rules

Deep dives by topic:

references/comprehensive/notation.md -- notation principles, implicit conventions, TeX macros, disambiguation
references/comprehensive/theorems-and-proofs.md -- theorem/lemma hierarchy, proof structure, statement design
references/comprehensive/paper-structure.md -- title, abstract, introduction, body, conclusions, appendices
references/comprehensive/english-usage.md -- sentence structure, word choice, logical connectives, common errors
references/comprehensive/reader-centered-writing.md -- audience awareness, examples, signposting, assertion status
references/comprehensive/citations-and-references.md -- signposting citations, specific references, journal selection
references/comprehensive/revision-and-process.md -- drafting workflow, revision strategy, collaboration, reading math

Sources

Tao, T. "Advice on Writing Papers" (6 posts). terrytao.wordpress.com.
Knuth, D., Larrabee, T., and Roberts, P. Mathematical Writing. 1989.
Cohn, H. "Advice." cohn.mit.edu.
Poonen, B. "Practical Suggestions for Mathematical Writing." MIT.
Conrad, K. "Advice on Mathematical Writing." UConn.
Su, F. E. "Guidelines for Good Mathematical Writing."
Tsitsiklis, J. N. "A Few Tips on Writing Papers with Mathematical Content."
Lagarias, J. C. "How to Write a Math Paper."
Goldreich, O. "How to Write a Paper."
Pak, I. "How to Write a Clear Math Paper: Some 21st Century Tips."
Trzeciak, J. Writing Mathematical Papers in English. EMS, 1995.
Berndt, B. C. "How to Write Mathematical Papers." UIUC.
Krantz, S. G. "How to Write Your First Paper." AMS, 2007.
Wang, R. "Suggestions for Writing Mathematics in Scientific Papers." 2024.
Lee, K. P. "A Guide to Writing Mathematics." MIT.
MIT 18.821. "Notes on Writing Mathematics."
Cambridge. "A Brief Guide to Mathematical Writing."

Read the full file on GitHub · 75 lines

Files

What ships with it

8 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.

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.

8d ago Changed · +1 lines · +13 tokens per session 97a82e00430b
26d ago Changed · -10 lines · -141 tokens per session 309b1b658cd6
1mo ago Changed bc03d7e1500e
1mo ago First seen · 84 lines · 169 tokens per session scan A 7b97b2310125

Subscribe to this mod's changes

write-math is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 761 once invoked, about $0.0002 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 2026-09-03.

Claude Code Scientific Writing and docs claude code style code-style-guide hooks macos

hypothesis-generation

Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Use when turning observations or preliminary findings into transparent, testable research plans without treating…

agentlas-ai/agentlas-desktop · 58 tokens

datamol

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…

agentlas-ai/agentlas-desktop · 67 tokens

reference

Optional method and tool reference for the Research Director -- stage playbooks, the research-loop and episode mechanics, tool routing, statistical execution and figures, and domain packs. Advice to consult when useful, not a required order.

agentlas-ai/agentlas-desktop · 46 tokens

direct-study

Drive a scientific study with data-first experiments and hypothesis revision, parallel literature, evidence-supported analysis and conclusions, then an appropriate manuscript, using phases as evidence milestones while preserving exact source, run, artifact, decision, analysis-plan, manuscript, and journal-validation…

agentlas-ai/agentlas-desktop · 55 tokens

analyze

Run deterministic local descriptive, explicit probability-distribution fitting, inferential, nonparametric, regression, bounded Gaussian random-intercept mixed-model, two-factor response-surface, survival, multivariate PCA, time-series diagnostic, contingency, correction, and confidence-interval analyses with…

agentlas-ai/agentlas-desktop · 62 tokens

deextinction-feasibility

Decompose a dinosaur revival question into independently evidenced stages with explicit stop conditions and Research Director review.

agentlas-ai/agentlas-desktop · 26 tokens

write-math