Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/LigphiDonk/Oh-my--papernpx agentmods add commands/ligphidonk/oh-my--paper/surveyWrote 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/commands/ligphidonk/oh-my--paper/survey)<a href="https://agentmods.dev/commands/ligphidonk/oh-my--paper/survey"><img src="https://agentmods.dev/badge/commands/ligphidonk/oh-my--paper/survey/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/commands/ligphidonk/oh-my--paper/survey"><img src="https://agentmods.dev/badge/commands/ligphidonk/oh-my--paper/survey.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 | $0.00021 | $0.01240 |
| Opus 5 | $0.00010 | $0.00620 |
| Sonnet 5 | $0.00004 | $0.00248 |
| Haiku 4.5 | $0.00002 | $0.00124 |
Grade A, and why
survey 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 9d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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。执行文献调研前先和用户对齐方向，然后下载真实论文 PDF 并 OCR，让 ideation 阶段能读到真实论文内容。
第一步：读取研究主题
cat .pipeline/memory/project_truth.md
cat .pipeline/docs/research_brief.json
cat .pipeline/memory/literature_bank.md # 查看已有多少文献
第二步：展示搜索计划，等待确认
用 AskUserQuestion 展示：
准备搜索以下方向的文献：
- [方向 A]（关键词：...）
- [方向 B]（关键词：...）
- [方向 C]（关键词：...）
目标：约 20-30 篇，已有 X 篇 工具： literature-pdf-ocr-library（真实 PDF + OCR）+ inno-deep-research
选项：
确认，开始搜索调整搜索方向只搜某个方向我有具体的 arXiv ID 列表，直接下载
如果用户选择调整，AskUserQuestion 询问具体方向修改，更新后再确认一次。
如果用户提供了 arXiv ID 列表，直接进入第三步用 --arxiv-ids 模式。
第三步：询问 OCR 方式（下载前必须确认）
用 AskUserQuestion 询问：
下载 PDF 后需要 OCR 转 Markdown，供后续 ideation 阅读真实论文内容。请选择 OCR 方式：
选项：
使用 PaddleOCR API（高质量布局识别，需要 Token）使用 pdfminer 本地模式（纯文本，无需 Token）只下载 PDF，暂不 OCR
如果用户选择 PaddleOCR API：
用 AskUserQuestion 继续询问：
请提供你的 PADDLEOCR_TOKEN（仅用于本次会话，不会写入任何文件）：
如果用户选择 pdfminer：
用 AskUserQuestion 再次确认：
pdfminer 只提取纯文本，没有图表和公式布局识别。确认用 pdfminer 继续？
选项：
确认，用 pdfminer 继续等我找到 PaddleOCR Token 再说
第四步：执行下载 + OCR（仅在确认后）
4a. 下载论文
corpus-name 根据研究主题自动命名（短横线格式，如 humanoid-locomotion）。
# 如果用户提供了 arXiv IDs
python .claude/skills/literature-pdf-ocr-library/scripts/search_and_download_papers.py \
--arxiv-ids <id1> <id2> ... \
--out-dir .pipeline/literature/<corpus-name> \
--download-pdfs
# 如果按关键词搜索
python .claude/skills/literature-pdf-ocr-library/scripts/search_and_download_papers.py \
--query "<搜索关键词>" \
--out-dir .pipeline/literature/<corpus-name> \
--limit 20 --sources arxiv semanticscholar openalex \
--download-pdfs
4b. OCR 转 Markdown
# PaddleOCR API（用户提供 Token）
export PADDLEOCR_TOKEN="<用户提供，不要写入文件>"
python .claude/skills/literature-pdf-ocr-library/scripts/paddleocr_layout_to_markdown.py \
.pipeline/literature/<corpus-name>/papers/*/paper.pdf \
--output-dir .pipeline/literature/<corpus-name>/papers \
--skip-existing
# pdfminer fallback（用户已通过 AskUserQuestion 确认）
python .claude/skills/literature-pdf-ocr-library/scripts/paddleocr_layout_to_markdown.py \
.pipeline/literature/<corpus-name>/papers/*/paper.pdf \
--output-dir .pipeline/literature/<corpus-name>/papers \
--fallback-pdfminer
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.
- 9d ago First seen · 137 lines · 21 tokens per session scan A b29c6e0fa527
survey is a command published in the GitHub repository LigphiDonk/Oh-my--paper (721 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 1,240 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.
Other commands, from other repositories
open
Open a PDF in the in-app viewer panel.
brief-compliance-check
Check a LaTeX coursework submission against the requirements in a supplied PDF assessment brief. Use when verifying format, required sections, word limits, or deliverables before submission. Not for general prose proofreading; use $proofread.
pipeline-minutar-pdf
Pipeline completo de sentença judicial a partir de PDF (conversão, linha-tempo, relatório, análise, fundamentação, merge).
cti-report
Render case deliverables — relationship graph (PNG/SVG/Mermaid) and a polished PDF/DOCX assessment. Usage: /cti-report [--graph|--pdf].
docs
Document delivery with export to PPTX, DOCX, PDF formats.
cheatsheet
Generate a one-page exam cheatsheet from course-index and errors/log.md. Outputs to cheatsheet/final.md. Optionally convert to PDF.