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 instructions/laibniz/scholarfetch/agents-mdgit clone --depth 1 https://github.com/laibniz/scholarfetchWhat 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 | $0.00998 | $0.00998 |
| Opus 5 | $0.00499 | $0.00499 |
| Sonnet 5 | $0.00200 | $0.00200 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
scholarfetch AGENTS.md 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 2d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ScholarFetch Agent Guide
ScholarFetch is a stateful research environment for agents.
Use it to build and refine a literature set over multiple MCP calls, not just to fetch isolated papers.
What The Agent Should Optimize For
- start broad, then narrow aggressively
- preserve only high-value papers in a named collection
- use abstracts for cheap triage
- use full text only for shortlisted papers
- expand references and authors only when they improve topic coverage
- export a compact artifact for downstream synthesis
Mental Model
ScholarFetch exposes a research tree:
- topic -> papers
- paper -> abstract
- paper -> full text
- paper -> references
- paper -> authors
- author -> papers
The collection parameter is the agent's working memory inside one MCP server process.
Primary Tool Roles
Discovery
scholarfetch_searchscholarfetch_doi_lookupscholarfetch_author_candidates
Use these to establish seed nodes.
Traversal
scholarfetch_author_papersscholarfetch_references
Use these to move through the literature graph.
Reading
scholarfetch_abstractscholarfetch_article_text
Use these to decide whether a paper deserves inclusion.
Curation
scholarfetch_saved_addscholarfetch_saved_listscholarfetch_saved_removescholarfetch_saved_clearscholarfetch_saved_export
Use these to keep a coherent reading list and hand off the result.
Recommended Agent Loop
- Run
scholarfetch_searchwith a topic query. - Save obviously relevant papers with
scholarfetch_saved_add. - For ambiguous authors, run
scholarfetch_author_candidates. - Expand the strongest author nodes with
scholarfetch_author_papers. - Read abstracts with
scholarfetch_abstract. - Read full text with
scholarfetch_article_textonly for shortlisted papers. - Expand references with
scholarfetch_referenceswhen a paper looks central or foundational. - Revisit the saved list with
scholarfetch_saved_list. - Remove weak papers with
scholarfetch_saved_remove. - Export with
scholarfetch_saved_export.
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.
- 2d ago First seen · 156 lines · 998 tokens per session scan A c219780158db
scholarfetch AGENTS.md is an instructions file published in the GitHub repository laibniz/scholarfetch (1 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 998 tokens to every session, about $0.0050 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 instructions, from other repositories
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.
designing-real-world-ai-agents-workshop CLAUDE.md
Instructions for iusztinpaul/designing-real-world-ai-agents-workshop, covering project, project structure, tech stack, access documentation and running qa.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
canvas-lms-mcp AGENTS.md
Instructions for bruchris/canvas-lms-mcp, covering agents.md — canvas lms mcp server, quick start, run with npx (no install needed), or install globally and architecture.
obsidian-university-workflow CLAUDE.md
Instructions for ABO896/obsidian-university-workflow, covering obsidian university workflow, project structure, rules for working on this project, templater api — always read the docs first and config alignment.
paper-pilot CLAUDE.md
Instructions for aytzey/paper-pilot, covering claude.md, best fit, setup, first workflow to try and claude prompt patterns.