What is daily_arxiv_digest AGENTS.md?

Repository instructions for Daily arXiv Digest, a command-line tool that reads arXiv, a website for sharing scientific papers, rates papers against chosen topics with a language model, and creates daily Markdown and JSON digests.

Use them when developing, running or testing the digest, including fetching papers, rebuilding results at a new relevance threshold and checking the basic language-model integration.

They tell a coding agent how the project is structured, how to run it and how to test it, reducing guesswork when changing the code.

How yang3kc/daily_arxiv_digest configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to yang3kc/daily_arxiv_digest. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/yang3kc/daily_arxiv_digest/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/yang3kc/daily_arxiv_digest

Made for: Claude Code, Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/yang3kc/daily_arxiv_digest/agents-md/github.svg)](https://agentmods.dev/instructions/yang3kc/daily_arxiv_digest/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/yang3kc/daily_arxiv_digest/agents-md"><img src="https://agentmods.dev/badge/instructions/yang3kc/daily_arxiv_digest/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/yang3kc/daily_arxiv_digest/agents-md"><img src="https://agentmods.dev/badge/instructions/yang3kc/daily_arxiv_digest/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,787 This file is loaded in full into every session.

When invoked 1,787 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01787	$0.01787
Opus 5	$0.00894	$0.00894
Sonnet 5	$0.00357	$0.00357
Haiku 4.5	$0.00179	$0.00179

Measured 9d ago against content hash cbd3a0425f78, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

daily_arxiv_digest 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 9d 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to AI coding agents when working with code in this repository. (CLAUDE.md includes it via @AGENTS.md.)

Project Overview

Daily arXiv Digest is a headless CLI tool that fetches papers from arXiv RSS feeds, uses an LLM to rate their relevance against user-defined topics, and writes a daily digest to digests/YYYY-MM-DD/ as both markdown (for humans) and JSON (for agents). It is designed to run unattended in a cron job or be invoked by another agent.

Commands

Development and Running

make run or make all - Generate today's digest
uv run python main.py - Direct command (flags: --config, --date, --force)
uv run python main.py --rethreshold X - Rebuild digest-.md/digest-.json from saved scores-.json at threshold X (no fetch/re-score; TL;DRs cached in tldrs-.json)
uv sync - Install/update dependencies

Testing

uv run python test_llm.py - Basic integration check: fetches one feed, scores one paper, writes one TL;DR

Architecture

Core Components

main.py - CLI entry point (argparse); loads .env, handles the already-exists/--force check
src/digest.py - Pipeline orchestration: fetch → score → select → TL;DR → render/write
src/rss.py - ArxivRSS class handles fetching papers from arXiv RSS feeds
src/llm.py - Provider registry (PROVIDERS), create_client(), and LLMPaperReader (relevance scoring + TL;DR generation)
src/logger.py - JSONL activity logging to logs/activity.jsonl; inspect with check_log.py

Key Design Patterns

Idempotent runs: Output is keyed by date; if digests/<date>/digest-<date>.json exists the run exits cleanly (exit 0) without API calls, unless --force
Multi-provider via one code path: OpenAI, Anthropic, and OpenRouter are all accessed through the OpenAI SDK (base_url override + per-provider API key env var); structured output via chat.completions.parse with Pydantic models
Concurrent Processing: ThreadPoolExecutor (50 workers by default) for both scoring and TL;DR phases
Error Resilience: Retry logic with graceful fallbacks — failed scoring returns neutral (0.0) judgements, failed TL;DRs return empty strings, so a batch never aborts
Configuration-Driven: All settings (topics, arXiv subjects, provider/model, threshold, output dir) are in config.json

Read the full file on GitHub · 93 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.

9d ago First seen · 93 lines · 1,787 tokens per session scan A cbd3a0425f78

Subscribe to this mod's changes

daily_arxiv_digest AGENTS.md is an instructions file published in the GitHub repository yang3kc/daily_arxiv_digest (21 stars, last pushed 14d ago), licensed MIT. It adds 1,787 tokens to every session, about $0.0089 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.

Claude Code LLM agent-skills arxiv claude-plugin paper-digest

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

daily_arxiv_digest: Instructions file for Claude Code