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 agentmods add skills/poco-ai/agentero/paper-readernpx skills add poco-ai/Agentero --skill paper-readergit clone --depth 1 https://github.com/poco-ai/AgenteroWrote 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/poco-ai/agentero/paper-reader)<a href="https://agentmods.dev/skills/poco-ai/agentero/paper-reader"><img src="https://agentmods.dev/badge/skills/poco-ai/agentero/paper-reader.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 | $0.00052 | $0.02226 |
| Opus 5 | $0.00026 | $0.01113 |
| Sonnet 5 | $0.00010 | $0.00445 |
| Haiku 4.5 | $0.00005 | $0.00223 |
Grade A, and why
paper-reader 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Reader
Role
You are a senior researcher who explains complex papers with extreme clarity: high-level first, then details. Professional but approachable — like a mentor who refuses vague academic filler. Prefer concrete examples over empty jargon.
Inputs (Agentero vault)
- Target is a paper folder under
papers/(Vault-relative path, e.g.papers/1706.03762or nestedpapers/nlp/1706.03762). - Read order (prefer earlier):
source/**/*.{tex,ltx}(arXiv e-print / LaTeX){paper}/PAPER.md(liteparse / structured body)- If no TeX or
PAPER.mdexists, runagentero paper parse {paper}and then read the generatedPAPER.md - Local PDF under the paper folder (e.g.
{id}.pdf)
- Existing
{paper}/NOTES.mdmay already have a title/abstract shell from Agentero import.- Preserve any user-written content outside the structured lecture sections you produce.
- Fill or replace the structured lecture body (sections below).
- Ensure YAML frontmatter
aliasesand note-creation date (see below).
- Do not delete
marks/,source/,assets/,attachments/, or binary files. - Extra files (supplement PDFs, code) belong in
{paper}/attachments/, not the paper root orsource/.
Activation notes (CLI differences)
Agentero may inject this entire SKILL.md into the prompt. Depending on the agent:
- Codex: skill trigger is
$paper-reader - Claude: skill trigger is often
/paper-reader - Other agents: follow the injected body; do not wait for a separate
$//command
Always execute the workflow even if no native skill runtime fires.
Frontmatter (required)
Agentero indexes Obsidian-style YAML frontmatter. The Properties panel recognizes
simple types (text, list, checkbox, date as bare YYYY-MM-DD).
Keep the on-disk file name as NOTES.md; do not rename the note to the paper title.
At the top of {paper}/NOTES.md, ensure a frontmatter block that includes at least:
---
aliases:
- <Full paper title>
- <Short title>
created: 2026-08-05
---
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.
- 4d ago First seen · 190 lines · 52 tokens per session scan A 44ae17511acc
paper-reader is a skill published in the GitHub repository poco-ai/Agentero (409 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 2,226 once invoked, about $0.0003 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 skills, from other repositories
当用户需要对PDF文件进行任何操作时,请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片,以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF,请使用此技能。.
pptx
当涉及到 .pptx 文件的任何操作时使用此技能——无论是作为输入、输出还是两者兼有。包括:创建幻灯片、演示文稿或路演材料;读取、解析或提取任何 .pptx 文件中的文本(即使提取的内容将用于其他地方,如邮件或摘要);编辑、修改或更新现有演示文稿;合并或拆分幻灯片文件;处理模板、布局、演讲者备注或批注。当用户提到“演示文稿”、”幻灯片“、”PPT“或引用 .pptx 文件名时触发,无论他们之后打算如何使用内容。如果需要打开、创建或操作 .pptx 文件,就使用此技能。.
adk-unit-design
Writes an as-built architecture document for one ADK code unit — purpose, execution flow, data flow, cross-class dependencies, extension points, and the parts that must not change — to docs/design/{topic}/{unit}/index.md. It describes the code as implemented, not a proposed design, and its reader is a developer about…
nano-pdf
Edits PDF files using natural-language instructions via the nano-pdf CLI. Supports modifying text, changing titles, fixing typos, and updating content on specific pages. Use when the user wants to edit a PDF, modify PDF content, update PDF text, fix a typo in a PDF, change a PDF title, or rewrite part of a PDF page.
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…
pdf-toolkit
Structured .pdf operations: extract text/tables, merge pages from multiple PDFs, split a PDF by page ranges, fill PDF form fields, and generate fresh PDFs from JSON. Trigger when the user wants programmatic PDF work without natural-language rewriting — examples: pull tables from a report, combine three PDFs, extract…