scholarfetch AGENTS.md

Instructions for ScholarFetch, a research environment for finding and organizing academic papers. It treats papers, abstracts, full text, references, and authors as connected parts of a literature set.

In plain words
What is it for?
It supports literature searches, finding papers by author or DOI, following references, reviewing abstracts or articles, and exporting a compact research set.
Why use it?
It helps an agent narrow a broad search while keeping only useful papers in a named collection. Abstracts can be used for quick screening before reading full text.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/laibniz/scholarfetch/agents-md
Clone the repo
git clone --depth 1 https://github.com/laibniz/scholarfetch

Made for: Codex, OpenCode.

Per session 998 This file is loaded in full into every session.
When invoked 998 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00998 $0.00998
Opus 5 $0.00499 $0.00499
Sonnet 5 $0.00200 $0.00200
Haiku 4.5 $0.00100 $0.00100

Measured 2d ago against content hash c219780158db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

AGENTS.md · 156 lines

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_search
  • scholarfetch_doi_lookup
  • scholarfetch_author_candidates

Use these to establish seed nodes.

Traversal

  • scholarfetch_author_papers
  • scholarfetch_references

Use these to move through the literature graph.

Reading

  • scholarfetch_abstract
  • scholarfetch_article_text

Use these to decide whether a paper deserves inclusion.

Curation

  • scholarfetch_saved_add
  • scholarfetch_saved_list
  • scholarfetch_saved_remove
  • scholarfetch_saved_clear
  • scholarfetch_saved_export

Use these to keep a coherent reading list and hand off the result.

  1. Run scholarfetch_search with a topic query.
  2. Save obviously relevant papers with scholarfetch_saved_add.
  3. For ambiguous authors, run scholarfetch_author_candidates.
  4. Expand the strongest author nodes with scholarfetch_author_papers.
  5. Read abstracts with scholarfetch_abstract.
  6. Read full text with scholarfetch_article_text only for shortlisted papers.
  7. Expand references with scholarfetch_references when a paper looks central or foundational.
  8. Revisit the saved list with scholarfetch_saved_list.
  9. Remove weak papers with scholarfetch_saved_remove.
  10. Export with scholarfetch_saved_export.

Read the full file on GitHub · 156 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. 2d ago First seen · 156 lines · 998 tokens per session scan A c219780158db

Subscribe to this mod's changes

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.