ml-intern

ml-intern is a skill for Claude Code from infiniV/ultra-ml-intern. It costs 131 tokens per session (2,134 once invoked), scanned B, original, MIT.

A research skill for answering machine-learning questions from the actual published papers rather than memory. It requires claims to be tied to specific papers, sections, and reported numbers.

In plain words
What is it for?
Literature reviews, citation-graph research, training-recipe extraction, field surveys, and identifying research gaps.
Why use it?
It helps avoid plausible but incorrect details about datasets, methods, results, or library interfaces. It also allows the answer to state clearly when a paper leaves something unspecified.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents; names the TodoWrite tool; mentions Claude Code.

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 Literature reviews, citation-graph research, training-recipe extraction, field surveys, and identifying research gaps.

Compare 6 skills 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-intern

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/infiniv/ultra-ml-intern/ml-intern"><img src="https://agentmods.dev/badge/skills/infiniv/ultra-ml-intern/ml-intern.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,134 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00131 $0.02134
Opus 5 $0.00066 $0.01067
Sonnet 5 $0.00026 $0.00427
Haiku 4.5 $0.00013 $0.00213

Measured 9d ago against content hash d324320ac5aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

ml-intern scanned grade B 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 9d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (scripts/crawl_arxiv.sh, scripts/download_paper.sh, scripts/hf_paper_meta.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

- **MCP server** — Hugging Face MCP at `https://huggingface.co/mcp`, declared in `.mcp.json`. Activates when the user has `HF_TOKEN` set; otherwise everything still works via `WebFetch` + the bundled shell helpers.
skills/ml-intern/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ML Intern — paper research

You are an ML research assistant. Your job is to answer methodology questions from published papers you actually read, not from training-time recall. Every claim you report is attributed to a specific paper, section, and number.

Core principles

Your memory of ML papers and HF library APIs is outdated and lossy. Citation counts, SOTA claims, dataset names, hyperparameters, and TRL/Transformers API shapes all drift. You will confidently produce a plausible recipe that no paper published. Read first, then write.

Read the paper, don't summarize a summary. paper_text.py writes a paper's real text to disk and you Read it. WebFetch answers a prompt using a small summarizer model, so its output is a paraphrase — quotes taken from it can't be verified and its section numbers are guesses. Use WebFetch for repos, docs, and Hub pages; never for papers.

Report what the evidence supports. A section that must be filled gets filled, and what fills it is invention. "No contradictions surfaced" and "the paper doesn't state a learning rate" are findings. A short report backed by real quotes beats a long one padded to look thorough.

Skip research only for trivial non-code questions.

The research loop

  1. Find the landmark paper(s) for the task or domain.
  2. Crawl the citation graph for recent downstream work — see references/paper-crawl.md.
  3. Read the most promising papers — fetch each to disk with paper_text.py, then read the method, experiments, and results. Recent + high-citation + strong benchmarks first. Abstracts lie by omission.
  4. Extract the recipe: dataset, training method, hyperparameters that produced the published result. Attribute every claim to a specific result (e.g. "Dataset X + method Y → 85.3% on benchmark Z, §4.2 Table 3").
  5. Validate the recipe against reality — does the dataset exist on Hub? Does the base model? Are the columns what the method needs?
  6. Report with working URLs: arXiv, Hub, and the paper's official repo.

Read the full file on GitHub · 148 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. 9d ago First seen · 148 lines · 131 tokens per session scan B d324320ac5aa

Subscribe to this mod's changes

ml-intern is a skill published in the GitHub repository infiniV/ultra-ml-intern (3 stars, last pushed 22d ago), licensed MIT. It adds 131 tokens to every session and 2,134 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

prompt-engineering

Create, update, review, or discuss an LLM prompt — a system prompt, a skill, or an agent. Use when writing or improving a prompt, discussing a skill or agent, diagnosing prompt failures, or when the user says a prompt needs work.

doodledood/manifest-dev · 56 tokens

review-prompt

Review LLM prompts against the prompt-engineering skill's principles — leading with where each line came from — and report the findings without modifying files. Use when reviewing prompt quality, auditing a prompt, evaluating a system prompt, or checking whether prompt issues are high-confidence and fixable.

doodledood/manifest-dev · 60 tokens

ccc-prompt-fix

Fix and sharpen a prompt. Diagnoses it against the 6 prompt-quality patterns, returns a tightened rewrite with the reasoning, and suggests the right library prompt for your task.

KevinZai/commander · 41 tokens

eval-set

Build and run a project-specific retrieval eval so changes to your rules or base prompt are scored, not eyeballed. Mirrors tests/groundtruth.json + clawness eval: you write prompt→expected-rule cases, then measure MRR@k and hit-rate before and after an edit. Run it after trimming a base prompt into ranked retrieval…

fullymiddleaged/Clawness · 98 tokens

oracle-grill-me

Grill the user relentlessly about a plan, decision, or idea, maintaining the project's domain model (CONTEXT.md, ADRs) as decisions crystallise. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

martinffx/atelier · 58 tokens

reinforcement-learning

Reinforcement Learning best practices for Python using modern libraries (Stable-Baselines3, RLlib, Gymnasium). Use when: Implementing RL algorithms (PPO, SAC, DQN, TD3, A2C) Creating custom Gymnasium environments Training, debugging, or evaluating RL agents Setting up hyperparameter tuning for RL Deploying RL models…

Aznatkoiny/zAI-Skills · 86 tokens