autoresearch

autoresearch is a skill for Claude Code from alfredolopez80/multi-agent-ralph-loop. It costs 61 tokens per session (8,134 once invoked), scanned A, original, no licence file.

An autonomous experiment loop that changes code, runs experiments, measures results, and keeps improvements. It is inspired by research workflows that repeatedly test and refine a program.

In plain words
What is it for?
It is for continuous optimization and repeated code experiments, including tasks started with `/autoresearch` or requests to optimize continuously.
Why use it?
It removes much of the manual repetition involved in trying code changes and comparing their results.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter.

Good fit It is for continuous optimization and repeated code experiments, including tasks started with /autoresearch or requests to optimize continuously.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alfredolopez80/multi-agent-ralph-loop/autoresearch
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 alfredolopez80/multi-agent-ralph-loop --skill autoresearch
Clone the repo
git clone --depth 1 https://github.com/alfredolopez80/multi-agent-ralph-loop

Made for: Claude Code.

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 autoresearch

README.md
[![agentmods](https://agentmods.dev/badge/skills/alfredolopez80/multi-agent-ralph-loop/autoresearch.svg)](https://agentmods.dev/skills/alfredolopez80/multi-agent-ralph-loop/autoresearch)
Your own site
<a href="https://agentmods.dev/skills/alfredolopez80/multi-agent-ralph-loop/autoresearch"><img src="https://agentmods.dev/badge/skills/alfredolopez80/multi-agent-ralph-loop/autoresearch.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,134 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 unknown 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 $0.00061 $0.08134
Opus 5 $0.00030 $0.04067
Sonnet 5 $0.00012 $0.01627
Haiku 4.5 $0.00006 $0.00813

Measured 8d ago against content hash 76a97152e66c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

autoresearch 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 8d 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.

.claude/skills/autoresearch/SKILL.md · 826 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 826 lines · 61 tokens per session scan A 76a97152e66c

Subscribe to this mod's changes

autoresearch is a skill published in the GitHub repository alfredolopez80/multi-agent-ralph-loop (146 stars, last pushed 4d ago), with no licence file. It adds 61 tokens to every session and 8,134 once invoked, about $0.0003 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.