paper-reading

paper-reading is a skill for Claude Code, Codex from Mizoreww/awesome-claude-code-config. It costs 100 tokens per session (2,383 once invoked), scanned A, original, MIT.

A guide for reading and critically reviewing academic papers from PDFs, web pages, URLs, or pasted text. It produces an evidence-based report instead of only a short summary.

In plain words
What is it for?
Use it to understand, summarize, or critique a research paper and create either a Markdown report or an interactive HTML report.
Why use it?
It helps readers follow how a paper supports its claims, including its methods, evidence, comparisons, limits, and implications. It also explains that bioRxiv-style or other academic papers need their technical details preserved when being summarized. [Note: the supplied description does not specifically mention bioRxiv.]

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to understand, summarize, or critique a research paper and create either a Markdown report or an interactive HTML report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mizoreww/awesome-claude-code-config/paper-reading
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 Mizoreww/awesome-claude-code-config --skill paper-reading
Clone the repo
git clone --depth 1 https://github.com/Mizoreww/awesome-claude-code-config

Made for: Claude Code, Codex.

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 paper-reading

README.md
[![agentmods](https://agentmods.dev/badge/skills/mizoreww/awesome-claude-code-config/paper-reading/github.svg)](https://agentmods.dev/skills/mizoreww/awesome-claude-code-config/paper-reading)
Your own site
<a href="https://agentmods.dev/skills/mizoreww/awesome-claude-code-config/paper-reading"><img src="https://agentmods.dev/badge/skills/mizoreww/awesome-claude-code-config/paper-reading/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 paper-reading

Your own site · 80×15
<a href="https://agentmods.dev/skills/mizoreww/awesome-claude-code-config/paper-reading"><img src="https://agentmods.dev/badge/skills/mizoreww/awesome-claude-code-config/paper-reading.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,383 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00100 $0.02383
Opus 5 $0.00050 $0.01192
Sonnet 5 $0.00020 $0.00477
Haiku 4.5 $0.00010 $0.00238

Measured 10d ago against content hash e04f3ec16b2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

paper-reading 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 10d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (assets/report.js, scripts/extract_paper.py, scripts/mathml_policy.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/paper-reading/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Paper reading

Treat a paper report as an argument with inspectable evidence, not a longer abstract. Preserve the familiar paper-type structure and the original technical template while cutting any sentence that adds no mechanism, evidence, comparison, limitation, or implication.

Resolve <skill-dir> as the directory containing this file before using bundled scripts or assets.

In examples, PYTHON_EXE means the actual interpreter of a compatible active or isolated environment—for example python3, python, py -3, or an absolute venv executable. Resolve it for the current platform; do not run the token literally or assume one command name exists.

1. Choose only the output format

Honor an explicit or clearly implied format. Otherwise ask once whether the user wants Markdown or HTML, then wait. Explain briefly: Markdown is light and editable; HTML adds the designed reading surface, one section outline, static mathematics, and click-to-enlarge visuals.

Do not ask for a reading level. Use one standard throughout: read the complete argument, retain all load-bearing technical detail, and write it concisely. Do not run reproduction experiments as part of this workflow.

Gate: record format; do not silently choose it when genuinely ambiguous.

2. Ground the source

Accept a local or remote PDF, official full-text HTML, or complete pasted text. Prefer PDF when available because page and figure anchors are stable; do not make PDF mandatory.

For a PDF, keep the source unchanged and extract into a new directory:

uv run --isolated --no-project --with pymupdf4llm==1.28.0 \
  python <skill-dir>/scripts/extract_paper.py PAPER.pdf EXTRACTED_DIR

If uv is unavailable, use an isolated standard venv. Reuse an already-compatible environment when possible. Never require Conda or install into a base, system, or global environment.

The extractor writes page-anchored text, source hashes, and an immutable assets/raw/ manifest. Copy selected visuals into the report; never delete raw extraction to “clean” it.

Read the full file on GitHub · 127 lines

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. 10d ago First seen · 127 lines · 100 tokens per session scan A e04f3ec16b2d

Subscribe to this mod's changes

paper-reading is a skill published in the GitHub repository Mizoreww/awesome-claude-code-config (259 stars, last pushed 7d ago), licensed MIT. It adds 100 tokens to every session and 2,383 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 2026-08-30.

Related

Other skills, from other repositories