auto-research

auto-research is a skill for Claude Code from airas-org/airas. It costs 104 tokens per session (1,999 once invoked), scanned A, original, MIT.

A skill for running an end-to-end machine-learning research project with AIRAS, while its backend language model performs the generation steps. It covers paper discovery, hypotheses, experiment design, repositories, analysis, and paper writing.

In plain words
What is it for?
Use it to find papers, propose and test machine-learning ideas, prepare an experiment repository, analyze results, and write a research paper. It requires configured language-model and GitHub credentials.
Why use it?
It provides a repeatable workflow for turning research questions into experiments and written results, while fitting the design to available computing hardware.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the airas plugin — 9 skills, 3 hooks, 1 MCP server shipped together

Good fit Use it to find papers, propose and test machine-learning ideas, prepare an experiment repository, analyze results, and write a research paper. It requires configured language-model and GitHub credentials.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/airas-org/airas/auto-research
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.

Any agent
npx skills add airas-org/airas --skill auto-research
Clone the repo
git clone --depth 1 https://github.com/airas-org/airas

Made for: Claude Code.

Or install airas, the plugin that ships this one along with the rest of its 9 skills, 3 hooks, 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 auto-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/airas-org/airas/auto-research/github.svg)](https://agentmods.dev/skills/airas-org/airas/auto-research)
Your own site
<a href="https://agentmods.dev/skills/airas-org/airas/auto-research"><img src="https://agentmods.dev/badge/skills/airas-org/airas/auto-research/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 auto-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/airas-org/airas/auto-research"><img src="https://agentmods.dev/badge/skills/airas-org/airas/auto-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,999 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 113
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
How audits are shown
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 $0.00104 $0.01999
Opus 5 $0.00052 $0.01000
Sonnet 5 $0.00021 $0.00400
Haiku 4.5 $0.00010 $0.00200

Measured today against content hash b6059399bc24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

auto-research 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 today.

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.

plugins/airas/skills/auto-research/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AIRAS research orchestrator

This file owns the order and the invariants; nothing else. Each step's how-to lives in its own skill — invoke it on entering the step and follow it over anything more generic. The steps themselves are deliberately independent: they state what repository state they need and what they leave behind, and only this file says which comes after which.

Flow

Run these skills in order:

  • setup-repository — experiment repo created and cloned
  • discover-papers — literature into a study list
  • hypothesize-and-design — falsifiable hypothesis; run ids and metrics settled; research context committed
  • preregister-paper — the full paper written and committed before any experiment; this commit is the freeze point
  • write-experiment-code — code to the execution and airas-eval contracts, environment fixed by lockfile + Dockerfile
  • run-experiments — execute on the platform, bring results back with provenance
  • analyze-results — analysis and verifiable figures
  • publish-paper — numbers realized from declarations, compile + recompute + provenance checks until green locally, then push: CI re-runs the verification, builds the PDF, commits it back onto the protected branch as paper.pdf and uploads it as the artifact — the paper of record — which is handed to the user, state persisted

Execution platform references live in _shared/references/ per platform.

Settle once, up front

Operational choices otherwise surface one tool default at a time, mid-flow. Ask the user for them together before starting the flow and carry the answers through the session:

  • repository visibility — prepare_repository defaults to private
  • execution platform; for Seyval, managed vs BYO compute and, when several exist, which workspace
  • compute target (GPU and architecture) — the experimental design and the dependency lockfile depend on it

Invariants across steps

These are the orchestrator's own rules; no step may relax them.

Read the full file on GitHub · 166 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. today Changed · +10 lines b6059399bc24
  2. 4d ago Changed · +1 lines 0636d9734382
  3. 5d ago Changed · +74 lines · +4 tokens per session a153884671ee
  4. 9d ago First seen · 81 lines · 100 tokens per session scan A 5614732144a8

Subscribe to this mod's changes

auto-research is a skill published in the GitHub repository airas-org/airas (32 stars, last pushed yesterday), licensed MIT. It adds 104 tokens to every session and 1,999 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 2026-08-30.

Related

Other skills, from other repositories

research-proof

Turn vague research ideas, math-heavy claims, AI-lab style agent loops, benchmark claims, causal claims, prototype-readiness claims, design research, prompt-injection-sensitive evidence reviews, and medical-research style questions into falsifiable proof programs with fixed Claim/Verifier/Current…

tonyblu331/research-proof · 101 tokens

proof-checker

A mathematical proof review and repair workflow for LaTeX documents. It checks whether a proof has valid reasoning, addresses identified gaps, reviews the fixes, and produces an audit report.

wanshuiyin/Auto-claude-code-research-in-sleep · 87 tokens

auto-paper-improvement-loop

An automated editing cycle for a compiled research paper: an external language model reviews it, fixes are applied, and the paper is compiled again.

wanshuiyin/Auto-claude-code-research-in-sleep · 67 tokens

paper-write

A workflow for writing a research paper section by section in LaTeX, a text format used to prepare structured technical documents. It starts from a paper outline and supports several academic venues and citation sources.

wanshuiyin/Auto-claude-code-research-in-sleep · 50 tokens

research-lit

Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.

wanshuiyin/Auto-claude-code-research-in-sleep · 48 tokens

paper-illustration

A workflow for generating academic illustrations, such as architecture diagrams and method visuals, with image generation and repeated review. Claude plans and checks the figure during the process.

wanshuiyin/Auto-claude-code-research-in-sleep · 67 tokens