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/brycewang-stanford/lit-review-agent-toolsnpx agentmods add skills/brycewang-stanford/lit-review-agent-tools/literature-review-toolsWrote 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/brycewang-stanford/lit-review-agent-tools/literature-review-tools)<a href="https://agentmods.dev/skills/brycewang-stanford/lit-review-agent-tools/literature-review-tools"><img src="https://agentmods.dev/badge/skills/brycewang-stanford/lit-review-agent-tools/literature-review-tools/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/brycewang-stanford/lit-review-agent-tools/literature-review-tools"><img src="https://agentmods.dev/badge/skills/brycewang-stanford/lit-review-agent-tools/literature-review-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00288 | $0.03605 |
| Opus 5 | $0.00144 | $0.01802 |
| Sonnet 5 | $0.00058 | $0.00721 |
| Haiku 4.5 | $0.00029 | $0.00361 |
Grade A, and why
literature-review-tools scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
call the API directly (`WebFetch`/`curl`). [`reference/apis/`](reference/apis/) has a How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Literature Review Tools — Select & Run
A curated, use-case-organized catalog of the strongest open-source AI tools for literature review — plus a launcher that actually installs and runs the top ones. Covers: end-to-end research agents, deep-research / auto-survey generators, autonomous "idea→paper" systems, citation-backed RAG over PDFs, PRISMA screening, MCP servers, Zotero/Obsidian integrations, PDF→structured extraction, citation graphs, and paper-writing / peer-review assistants.
Full source of truth (README, always current star counts): https://github.com/brycewang-stanford/lit-review-agent-tools
Three modes
- Look up — user wants the literature itself: "find papers on X", "get me the PDF for this DOI", "does this citation exist", "what does PubMed have since 2022". Answer it directly — no install, no key. Start with
reference/apis/README.mdfor one-off lookups, or run the bundledpapers-fetch/oa-resolvescripts for anything corpus-sized. - Recommend — user asks "what should I use to …". Route with the tables below; cite the catalog for details.
- Run — user asks to install / run / use a specific tool ("turn this PDF into Markdown with MinerU", "ask PaperQA2 about these papers", "set up the arXiv MCP server"). Drive
scripts/litrun.pyvia Bash — do not hand the user raw pip commands to copy.
Mode 1 is the cheap default. Do not send someone to install PyTorch when they asked for five papers and a PDF.
Look up mode — search without installing anything
Two bundled scripts, both standard-library only: no venv, no pip, no API key.
Run them straight (python3 scripts/fetch_papers.py …) or through the launcher.
# 1. search six indexes at once, deduplicated by DOI
python3 scripts/fetch_papers.py --query "active learning for screening" \
--sources openalex,crossref,semanticscholar,pubmed,europepmc,arxiv \
--max 15 --dedup-titles --outdir ./corpus
# 2. turn those DOIs into full text you may legally read
python3 scripts/resolve_oa.py --from-json ./corpus/results.json --outdir ./corpus
What ships with it
17 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.
- recipes/recipes.json 13 KB
- recipes/workflows.json 8.5 KB
- reference/apis/arxiv.md 2.6 KB
- reference/apis/crossref.md 2.8 KB
- reference/apis/europepmc.md 2.8 KB
- reference/apis/open-access.md 4.0 KB
- reference/apis/openalex.md 3.2 KB
- reference/apis/pubmed-pmc.md 3.6 KB
- reference/apis/README.md 5.1 KB
- reference/apis/semantic-scholar.md 2.5 KB
- reference/catalog.md 16 KB
- scripts/fetch_arxiv.py 3.9 KB runs code
- scripts/fetch_openalex.py 4.5 KB runs code
- scripts/fetch_papers.py 21 KB runs code
- scripts/fetch_pubmed.py 4.2 KB runs code
- scripts/litrun.py 21 KB runs code
- scripts/resolve_oa.py 13 KB runs code
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 · 182 lines · 288 tokens per session scan A c692ff66b5ae
literature-review-tools is a skill published in the GitHub repository brycewang-stanford/lit-review-agent-tools (16 stars, last pushed 5d ago), licensed CC0-1.0. It adds 288 tokens to every session and 3,605 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-newbie-guide
A beginner-facing guide for turning vague ideas into clear, actionable requests for a coding agent. It keeps technical system details hidden during the conversation.
agent-patterns-catalog
A reference catalogue of six common AI-agent designs, including agents that reason and act, retrieve documents, call tools, coordinate several agents, or work autonomously. It compares their structures, data flow, and suitable uses without tying them to one framework.
agent-learning-coach
A Chinese-language learning coach for programming, English, design, product work, AI, mathematics, or other skills. It first checks the learner's level, then teaches through explanations, exercises, feedback, and review.
keshav-three-pass
Tactic: Read one paper by Keshav's three-pass method — a shallow skim, a contribution-grasping full read, then a deep virtual re-implementation. Use when the goal is understanding a paper rather than extracting a fixed schema.
challenge-operation
Non-threatening 'Why?' questioning of current practices (de Bono Challenge).
first-pass-skim
Keshav's first pass over one paper — a 5-10 minute skim of title, abstract, headings, figures, and conclusion only, producing skim notes and a read-deeper judgment. Use this as the first step whenever a paper is being read via the Keshav three-pass method; always precedes second-pass-grasp and never reads section…