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 BESSER-PEARL/research-agent-skills --skill research-paper-reviewgit clone --depth 1 https://github.com/BESSER-PEARL/research-agent-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/besser-pearl/research-agent-skills/research-paper-review)<a href="https://agentmods.dev/skills/besser-pearl/research-agent-skills/research-paper-review"><img src="https://agentmods.dev/badge/skills/besser-pearl/research-agent-skills/research-paper-review/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/besser-pearl/research-agent-skills/research-paper-review"><img src="https://agentmods.dev/badge/skills/besser-pearl/research-agent-skills/research-paper-review.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 | $0.00087 | $0.02041 |
| Opus 5 | $0.00044 | $0.01020 |
| Sonnet 5 | $0.00017 | $0.00408 |
| Haiku 4.5 | $0.00009 | $0.00204 |
Grade A, and why
research-paper-review 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 12d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Paper Review
Assist researchers in reviewing, analyzing, and criticizing academic papers systematically and thoroughly.
When to Use
- User asks to review, summarize, or critique a research paper
- User shares a PDF or link to an academic paper
- User wants to assess methodology, contributions, or novelty
- User needs help writing a peer review
- User wants to compare multiple papers or do a literature survey
- User wants to improve a paper before submission (pre-submission review)
- User wants to check for numerical/statistical inconsistencies
- User wants venue-specific feedback (conference, journal, or preprint)
Inputs
- Paper content: PDF, LaTeX source, or plaint text
- Target Venue (optional but recommended): conference, journal, or preprint target - Example: "Models 2026", "TOSEM", "Sosym", "arXiv preprint"
- Type of paper (important — ask the user if not provided): the review criteria change substantially by type. Common types: "full research" paper, "short" paper, "new ideas"/vision paper, "tool demo" paper, "poster", "extended abstract"/"short abstract", "journal"/"extended" paper. If the user does not state the type, ask before reviewing (or state the assumed type explicitly in the review).
- Explicit reviewing guidelines (optional): if available provide a description or URL with the reviewing criteria.
Review Workflow
###Step 0: Pre-Processing / Venue Context
- If target venue and/or the type of paper are provided, include them as context for all subsequent steps:
“Review this paper as if it is intended for [TARGET VENUE] as a [TYPE PAPER] submission. Consider typical standards, expectations, page limits, scope, and audience for this venue and type of paper”
- Calibrate expectations to the paper type. Do not apply full-paper standards to every submission. In particular, do not fault a paper for missing something its type does not require (e.g., do not criticize a tool demo paper for lacking a real-world validation study, or a vision paper for lacking large-scale experiments). Use the table below as the baseline, then adjust with the venue's own guidelines:
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.
- 12d ago First seen · 157 lines · 87 tokens per session scan A 5dab824b1af2
research-paper-review is a skill published in the GitHub repository BESSER-PEARL/research-agent-skills (17 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 2,041 once invoked, about $0.0004 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
awesome-abstract
A method for writing computer-science and AI research abstracts as a complete argument. It connects one clear limitation in earlier work to a method and evidence that addresses it.
research-code
A small, readable implementation of a university research paper, baseline, or experiment in deep learning. Deep learning is a type of machine learning that learns patterns from data using layered mathematical models.
graph-fraud
A set of checks for graph-based fraud detection, where connected data such as users, transactions, or accounts is examined for suspicious patterns. It follows the BWGNN research protocol on four named datasets: YelpChi, Amazon, T-Finance, and T-Social.
html-ppt-zhangzara-pin-and-paper
A field-biology capstone on urban pollinator decline — the survey design, the data, the contribution, and the caveats. Built as a decision-grade coursework defense deck for faculty reviewers.
academic-research
Nested swiss-knife reference for academic literature work — find papers, fetch full-text PDFs, trace citations, write LaTeX manuscripts. First action for any "get me this paper" request: python3 /scripts/fetchpaper.py — walks arXiv → Unpaywall → Europe PMC → CORE → in-house publisher-page extraction…
scientific-writing
Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting…