write

write is a command for coding agents from LigphiDonk/Oh-my--paper. It costs 20 tokens per session (666 once invoked), scanned A, original, MIT.

A Chinese-language workflow for writing a research paper one section at a time. It covers sections such as the abstract, introduction, related work, methods, experiments, and conclusion, with confirmation between sections.

In plain words
What is it for?
Use it for staged academic-paper writing when the project has source summaries, literature records, experiment results, and bibliography files.
Why use it?
It breaks a long paper into manageable stages and requires each section to be reviewed before continuing. It also instructs the writer to base claims and results on project files and real data.

Command

Part of the omp plugin — 9 commands, 5 agents, 3 hooks shipped together

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.

agentmods
npx agentmods add commands/ligphidonk/oh-my--paper/write
Clone the repo
git clone --depth 1 https://github.com/LigphiDonk/Oh-my--paper

Or install omp, the plugin that ships this one along with the rest of its 9 commands, 5 agents, 3 hooks.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/ligphidonk/oh-my--paper/write.svg)](https://agentmods.dev/commands/ligphidonk/oh-my--paper/write)
Your own site
<a href="https://agentmods.dev/commands/ligphidonk/oh-my--paper/write"><img src="https://agentmods.dev/badge/commands/ligphidonk/oh-my--paper/write.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 666 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00020 $0.00666
Opus 5 $0.00010 $0.00333
Sonnet 5 $0.00004 $0.00133
Haiku 4.5 $0.00002 $0.00067

Measured 4d ago against content hash 45f89cd41b96, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write 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.

plugins/oh-my-paper/commands/write.md · 91 lines

What it actually says

必须使用 AskUserQuestion 工具进行所有确认步骤,不得用纯文字替代。

你是 Oh My Paper Orchestrator。写作按节推进,每节完成后确认再继续。

第一步:确认写作范围

cat .pipeline/docs/result_summary.md
ls sections/

AskUserQuestion 展示:

准备写作的章节

  • abstract.tex
  • introduction.tex
  • related_work.tex
  • methodology.tex
  • experiments.tex
  • conclusion.tex(可选)

已有文件:[列出 sections/ 下已存在的]

选项:

  • 全部从头写
  • 只写缺少的章节
  • 指定某几节

第二步:按节逐步执行

每节开始前,先告知用户:

现在写 [节名],基于:[依赖的来源文件]

然后调用 Codex:

摘要 + 引言:

调用 inno-paper-writing skill,根据 .pipeline/memory/project_truth.md.pipeline/docs/result_summary.md,写 sections/abstract.texsections/introduction.tex,不捏造数据。

相关工作:

调用 inno-paper-writing skill,基于 .pipeline/memory/literature_bank.md(Status=accepted),写 sections/related_work.tex\cite{key} 引用必须存在于 references.bib

方法论:

调用 inno-paper-writing skill,基于 project_truth.md 中的方法描述,写 sections/methodology.tex,包含必要数学公式。

实验与结果:

调用 inno-paper-writing skill,基于 .pipeline/memory/experiment_ledger.mdresult_summary.md,写 sections/experiments.tex,使用真实数据。

每节完成后,用 AskUserQuestion 询问:

[节名] 已完成。你想:

选项:

  • 继续写下一节
  • 先看看这节写得怎么样
  • 这节有问题,让 Codex 修改
  • 暂停,稍后继续

第三步:图表和引用

所有节完成后,询问:

正文已完成。接下来:

选项:

  • 生成图表(architecture diagram、结果对比图)
  • 跳过图表,直接做引用审查
  • 两个都做

图表:

调用 inno-figure-gen skill,生成 2-3 个关键图表到 assets/figures/

引用审查:

调用 inno-reference-audit skill,检查所有 \cite{} 引用,修复缺失条目。

完成后

询问:

  • 进入 /omp:review 做同行评审
  • 我自己先看看再说
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. 4d ago First seen · 91 lines · 20 tokens per session scan A 45f89cd41b96

Subscribe to this mod's changes

write is a command published in the GitHub repository LigphiDonk/Oh-my--paper (721 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 666 once invoked, about $0.0001 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 2026-08-30.