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 whoisraibolt/paper-skills --skill paper-writergit clone --depth 1 https://github.com/whoisraibolt/paper-skillsWrote 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/whoisraibolt/paper-skills/paper-writer)<a href="https://agentmods.dev/skills/whoisraibolt/paper-skills/paper-writer"><img src="https://agentmods.dev/badge/skills/whoisraibolt/paper-skills/paper-writer/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.
<a href="https://agentmods.dev/skills/whoisraibolt/paper-skills/paper-writer"><img src="https://agentmods.dev/badge/skills/whoisraibolt/paper-skills/paper-writer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00109 | $0.02660 |
| Opus 5 | $0.00055 | $0.01330 |
| Sonnet 5 | $0.00022 | $0.00532 |
| Haiku 4.5 | $0.00011 | $0.00266 |
Grade A, and why
paper-writer 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 11d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paper-writer — redação segmentada com fundamentação obrigatória
Espelha a arquitetura do paper-reviewer (Paper Assistant Tool, Jayaram et al., Google Research, arXiv:2606.28277), mas para o lado da escrita em vez da crítica: segmentar o que falta escrever, dar a cada redator o manuscrito inteiro como contexto de voz e consistência, mas só um segmento como alvo de redação, e consolidar depois. A mesma lógica que eleva a taxa de detecção de erro no PAT — atenção concentrada em vez de uma passada rasa e uniforme — vale para produzir prosa consistente em vez de um rascunho genérico.
Não produz texto pronto pra publicar. Produz rascunho fundamentado, com toda alegação numérica rastreável a um artefato declarado, na voz definida pelo projeto — para o autor revisar e aprovar frase por frase. Diferente do paper-reviewer (só lê, nunca edita), esta skill escreve — por isso a disciplina de fundamentação abaixo é mais rígida, não mais frouxa: aqui uma alucinação vira afirmação falsa dentro do artigo, não um apontamento perdido num relatório.
Configuração do projeto — obrigatória, antes de qualquer coisa
Esta skill não escreve uma frase até saber de onde os números podem vir. Procure o arquivo de configuração nesta ordem:
.claude/paper-writer.mdna raiz do projetopaper-writer.config.mdna raiz do projeto- o caminho que o usuário indicar
Se não existir nenhum, pare e peça. Copie references/project-config.template.md (desta skill) para o projeto, peça ao usuário para preencher, e só então prossiga. Há um exemplo completo e preenchido em references/example-config-ptbr-abnt.md.
Escrever sem config é o modo de falha que esta skill existe para impedir: sem lista de artefatos canônicos, um redator com pressa preenche o buraco com um número plausível, e número plausível é indistinguível de número certo até o parecerista conferir.
O config declara quatro coisas:
| Bloco | O que é | Por que importa |
|---|---|---|
| Artefatos canônicos | os arquivos de onde os números podem vir | é a única fonte legítima |
| Fontes supersedidas | o que existe no repositório e está proibido como fonte | rascunho antigo e rodada de dados velha são o vetor de erro mais comum |
| Narrativa de processo a excluir | o que aconteceu mas não vai para o manuscrito | ver Regra dura 2 |
| Guia de voz | as convenções de escrita do projeto | é o que impede o rascunho de destoar do que já existe |
What ships with it
2 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.
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.
- 11d ago First seen · 138 lines · 109 tokens per session scan A 638bc75e2d5f
paper-writer is a skill published in the GitHub repository whoisraibolt/paper-skills (1 stars, last pushed 16d ago), licensed MIT. It adds 109 tokens to every session and 2,660 once invoked, about $0.0005 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
propose-economics-paper-titles
A writing guide for proposing and checking English titles for economics research papers. It covers empirical, theoretical, and structural papers.
write-economics-abstract
Always invoke this skill when the user wants an abstract or 摘要 for an economics research paper from a manuscript, completed paper body, model, data, or results—including requests to read an empirical, theoretical, or structural economics paper and write a ready-to-use English abstract. Use it to draft, rewrite…
write-economics-conclusion
Always invoke this skill when the user wants a conclusion, concluding section, final paper section, paper ending, or 结论 for an economics manuscript—including requests to read an empirical, theoretical, or structural economics paper and write a ready-to-use English conclusion. Use it to draft, rewrite, shorten, audit…
research-expert
Expert-level research methodology, academic writing, statistical analysis, and scientific investigation. Use when the user mentions methodology, statistics, academic writing, or experimental design, or when the task involves Research Design, Statistical Analysis, or Data Analysis.
paper-writer
Medical/scientific paper writing workflow skill. Manages the full pipeline from literature search to submission-ready manuscript. Creates and manages a project directory with IMRAD-format section files, literature matrix, reference management, and quality checklists. Supports both English and Japanese papers.…
food-research
Run a comprehensive, multi-source literature and evidence-synthesis workflow for food & nutrition science. Use when the user wants to research a food/nutrition topic in depth, do a literature review, build an evidence brief, screen and synthesize many sources, verify citations, or scope a systematic review.…