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 aniketkrs/research-paper --skill read-research-papergit clone --depth 1 https://github.com/aniketkrs/research-paperWrote 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/aniketkrs/research-paper/read-research-paper)<a href="https://agentmods.dev/skills/aniketkrs/research-paper/read-research-paper"><img src="https://agentmods.dev/badge/skills/aniketkrs/research-paper/read-research-paper/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/aniketkrs/research-paper/read-research-paper"><img src="https://agentmods.dev/badge/skills/aniketkrs/research-paper/read-research-paper.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 | $0.00172 | $0.03342 |
| Opus 5 | $0.00086 | $0.01671 |
| Sonnet 5 | $0.00034 | $0.00668 |
| Haiku 4.5 | $0.00017 | $0.00334 |
Grade A, and why
read-research-paper 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read Research Paper
Where the other two skills do this:
| Skill | What it does |
|---|---|
get-research-paper |
FINDS real papers on a topic |
research-paper |
WRITES new papers |
read-research-paper (this) |
READS ONE paper and makes it engaging |
Give it a URL, arXiv ID, DOI, or pasted text. It produces a visual, multi-layer rendering: technical depth + plain English + mind maps + method flowcharts + key-finding infographics + comparison tables + related-work timelines.
This file is the entry point. Heavier guidance lives in topic folders and is loaded on demand.
1. When to activate
Slash commands
| Command | What it does |
|---|---|
/read-research-paper <input> |
Full visual rendering (default) |
/read-paper <input> |
Alias |
/explain-paper <input> |
Same, with extra plain-English layer |
/visualize-paper <input> |
Same, emphasizing visuals over prose |
/tldr-paper <input> |
One-page infographic summary only |
<input> can be:
- A URL:
https://arxiv.org/abs/2403.01234,https://doi.org/...,https://example.com/paper.pdf, journal landing page, etc. - An arXiv ID:
2403.01234orcs.LG/0701002 - A DOI:
10.1145/3589334 - Pasted text: the paper's abstract or full body
- A local file in any supported format (see below).
Supported file formats
The skill reads any of these as input:
| Format | Extensions | Library used | Always available? |
|---|---|---|---|
| Markdown | .md, .markdown |
stdlib | yes |
| Plain text | .txt |
stdlib | yes |
| LaTeX | .tex, .latex |
stdlib + regex de-LaTeX | yes |
| JSON | .json |
stdlib | yes |
| HTML | .html, .htm |
beautifulsoup4 (or regex) | yes (regex fallback) |
| CSV / TSV | .csv, .tsv |
pandas (or stdlib) | yes (basic via stdlib) |
| RTF | .rtf |
striprtf (or regex) | yes (regex fallback) |
.pdf |
pdfplumber / pypdf | install one | |
| DOCX | .docx |
python-docx | install |
| PPTX | .pptx |
python-pptx | install |
| XLSX | .xlsx, .xls |
pandas + openpyxl | install |
| EPUB | .epub |
ebooklib | install |
| Images | .png, .jpg, .tiff, .bmp |
pytesseract + PIL | install (OCR) |
What ships with it
27 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.
- cache/README.md 1.3 KB
- corpus/anchor-papers.yaml 9.2 KB
- corpus/README.md 5.5 KB
- corpus/topics-index.yaml 3.0 KB
- examples/sample-visual-output.md 10 KB
- instructions/core.md 8.9 KB
- instructions/freshness.md 8.7 KB
- manifest.json 5.6 KB
- prompts/extract-findings.md 4.9 KB
- prompts/generate-mindmap.md 4.8 KB
- prompts/parse-paper.md 6.4 KB
- prompts/plain-english.md 7.2 KB
- prompts/visual-summary.md 5.0 KB
- schemas/visual-paper.json 6.7 KB
- sources/arxiv.md 3.1 KB
- sources/file-formats.md 7.6 KB
- sources/paper-parsing.md 5.1 KB
- sources/pdf-extraction.md 3.9 KB
- templates/infographic.md 3.8 KB
- templates/tldr.md 5.0 KB
- templates/visual-paper.md 6.8 KB
- toolchains/extract_pdf.py 6.4 KB runs code
- toolchains/fetch_paper.py 19 KB runs code
- toolchains/read_any_file.py 17 KB runs code
- workflows/caching.md 6.7 KB
- workflows/ingestion.md 8.9 KB
- workflows/visualization.md 7.0 KB
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 · 327 lines · 172 tokens per session scan A 03b8c2c8dd31
read-research-paper is a skill published in the GitHub repository aniketkrs/research-paper (4 stars, last pushed 3mo ago), licensed MIT. It adds 172 tokens to every session and 3,342 once invoked, about $0.0009 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
ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
acl-review-process
Use when reasoning about how an ACL paper travels through ACL Rolling Review and conference commitment, covering reviewer and area-chair roles, meta-reviews, the commitment decision by senior area chairs and program chairs, Findings versus main-conference outcomes, ethics review escalation, and resubmission strategy…
academic-paper-reviewer
Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on…
deep-research
Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring…
scholar-evaluation
Systematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and writing with quantitative scoring and actionable feedback.
rwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.