ml-paper-researcher

ml-paper-researcher is an agent for Claude Code from infiniV/ultra-ml-intern. It costs 108 tokens per session (2,043 once invoked), scanned A, original, MIT.

An agent that crawls machine-learning papers and citation links, then returns a small set of papers and code references for building a training script. It can search for papers, their references, and later papers that cite them.

In plain words
What is it for?
Finding landmark papers, follow-up work, datasets, methods, training settings, reported results, and official code for a machine-learning task.
Why use it?
It reduces the work of finding relevant research and tracing how methods developed. Its output is designed to support a recipe grounded in published results.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the ml-intern plugin — 4 skills, 2 commands, 2 agents, 1 MCP server shipped together

Good fit Finding landmark papers, follow-up work, datasets, methods, training settings, reported results, and official code for a machine-learning task.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add infiniV/ultra-ml-intern
Claude Code
/plugin install ml-intern

Made for: Claude Code.

Or install ml-intern, the plugin that ships this one along with the rest of its 4 skills, 2 commands, 2 agents, 1 MCP server.

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.

agentmods badge for ml-paper-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/infiniv/ultra-ml-intern/ml-paper-researcher/github.svg)](https://agentmods.dev/agents/infiniv/ultra-ml-intern/ml-paper-researcher)
Your own site
<a href="https://agentmods.dev/agents/infiniv/ultra-ml-intern/ml-paper-researcher"><img src="https://agentmods.dev/badge/agents/infiniv/ultra-ml-intern/ml-paper-researcher/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.

agentmods 80×15 button for ml-paper-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/infiniv/ultra-ml-intern/ml-paper-researcher"><img src="https://agentmods.dev/badge/agents/infiniv/ultra-ml-intern/ml-paper-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,043 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00108 $0.02043
Opus 5 $0.00054 $0.01022
Sonnet 5 $0.00022 $0.00409
Haiku 4.5 $0.00011 $0.00204

Measured 11d ago against content hash 7b09848982af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ml-paper-researcher 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.

agents/ml-paper-researcher.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ML Paper Researcher

You are an ML literature crawler. Your job: given a task description, return the smallest possible set of papers + code references that lets the main agent write a working training script grounded in published results.

Procedure

The steps below are the contract; endpoint details and rate limits live in ${CLAUDE_PLUGIN_ROOT}/skills/ml-intern/references/paper-crawl.md (read only if a call misbehaves). Start from papers, not docs — papers contain results, results tell you what works, then you back the recipe up with code.

Tools available in ${CLAUDE_PLUGIN_ROOT}/skills/ml-intern/scripts/:

Script Use
crawl_arxiv.sh "query" ML-tuned search via HF Papers (default; returns upvotes, not citations)
crawl_arxiv.sh "query" --min-cites N --date-from YYYY-MM-DD --field "Computer Science" --sort citationCount:desc Filtered search via S2 bulk (multi-word queries auto-phrase-quoted; --loose disables)
crawl_arxiv.sh --cited-by <id> --limit N Downstream citers — includes influential flag + intents
crawl_arxiv.sh --refs <id> --limit N References (with influence + intents)
crawl_arxiv.sh --info <id> Metadata + S2 tldr
paper_text.py <id> --dir ./papers --sections Fetch a paper's full text to disk, then Read it
snippet_search.sh "<claim>" Full-text passage search across 12M+ papers (needs S2_API_KEY)
recommend_papers.sh <id> Related papers when the citation graph is sparse
hf_paper_meta.sh <id> [--datasets|--models|--collections|--all] Linked Hub artifacts, sorted by downloads
inspect_dataset.sh <org/name> Validate dataset format on Hub

Crawl steps

  1. Find the anchor paper — two lanes. If the user gave an arxiv ID, start there. Otherwise:
    # Classic lane: who defined the approach
    crawl_arxiv.sh "<task description>" --min-cites 20 --sort citationCount:desc --limit 5
    # Frontier lane: newest work with traction — your SOTA-check set
    crawl_arxiv.sh "<task description>" --date-from <12mo-ago> --min-cites 5 --sort publicationDate:desc --limit 10
    
    The classic-lane winner is the anchor. Citation counts favor age — the current best recipe usually lives in the frontier lane or the anchor's recent citers, so never stop at the anchor.

Read the full file on GitHub · 141 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. 11d ago First seen · 141 lines · 108 tokens per session scan A 7b09848982af

Subscribe to this mod's changes

ml-paper-researcher is an agent published in the GitHub repository infiniV/ultra-ml-intern (3 stars, last pushed 24d ago), licensed MIT. It adds 108 tokens to every session and 2,043 once invoked, about $0.0005 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.

Related

Other agents, from other repositories

ai-eval-engineer

Builds and maintains the eval pipeline for ai-system / agent-product archetypes. Outputs tests/eval/EVAL-.md files (golden citation, refuse-when-uncertain, output schema, prompt injection, cost-overrun, cross-user isolation). Runs regression on every prompt or model change. Detects drift.

avelikiy/great_cto · 71 tokens

data-platform-reviewer

Data-platform pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off retention + lineage decisions before senior-dev claims tasks.

avelikiy/great_cto · 33 tokens

geo-routing-engineer

Geospatial and routing specialist for Product-Builder products with maps, scheduling-by-location, or vehicle routing (route-optimization in logistics, dispatch in home services, field-booking). Owns the routing contract — geocoding, the VRP/routing model (constraints, objective), maps/distance-matrix provider…

avelikiy/great_cto · 112 tokens

mlops-reviewer

MLOps / model lifecycle pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off training-pipeline + serving-strategy decisions before senior-dev claims tasks.

avelikiy/great_cto · 41 tokens

auth-engineer

Authentication and access-control specialist for SMB Product-Builder products. Owns the auth contract — provider choice (Auth.js default / Clerk fast-path), session model, RBAC, multi-tenant row-level isolation, the protected-route map, account lifecycle (signup/login/reset/invite), and OAuth/magic-link/password…

avelikiy/great_cto · 86 tokens

ai-agent

AI feature implementation specialist. Handles STT, LLM, and AI service integration with context-aware patterns. Auto-discovers project conventions before implementing. Supports OpenAI, Anthropic, and other AI providers with streaming, error handling, and cost optimization.

wigtn/wigtn-plugins · 54 tokens