plugin

autoresearch-agent — Claude Code plugin: what it does, how to install

Q: How to install autoresearch-agent in Claude Code?

Run `/plugin marketplace add alirezarezvani/claude-skills` to register the marketplace. Next, install the plugin using `/plugin install autoresearch-agent@claude-code-skills`.

Runs autonomous experiment loops to optimize any file against a measurable metric. Useful for recurring automated benchmark runs and code tuning.

Install into Claude Code · Plugin marketplace All methods and platforms ↓

/plugin marketplace add alirezarezvani/claude-skills
/plugin install autoresearch-agent@claude-code-skills

Open on GitHub

What autoresearch-agent does

This plugin manages autonomous research cycles that optimize project files against measurable metrics. It bundles 8 built-in evaluators to score benchmark runs and verify code changes.

Control relies on 5 slash commands: /ar:setup, /ar:ar-run, /ar:loop, /ar:ar-status, and /ar:ar-resume. The execution loop accepts configurable intervals ranging from 10 minutes to monthly. Without an explicit measurable metric, the evaluators cannot track progress.

What it helps with

run autonomous experiment loops on project files
benchmark code adjustments against 8 built-in evaluators
schedule recurring optimization runs with intervals from 10 minutes
check experiment progress with slash commands

Example prompts for the agent

/ar:setup
/ar:ar-run
/ar:ar-status

How to install autoresearch-agent

Plugin marketplace

/plugin marketplace add alirezarezvani/claude-skills

/plugin install autoresearch-agent@claude-code-skills

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about autoresearch-agent

How to install autoresearch-agent in Claude Code?

Run /plugin marketplace add alirezarezvani/claude-skills to register the marketplace. Next, install the plugin using /plugin install autoresearch-agent@claude-code-skills.

What does autoresearch-agent do?

It executes autonomous experiment loops to optimize files against a measurable metric using built-in evaluators.

Which loop intervals does autoresearch-agent support?

The loop can be configured for recurring execution from 10-minute intervals up to once a month.

Source text

autoresearch-agent · MIT

Autonomous experiment loop — optimize any file by a measurable metric. 5 slash commands (/ar:setup, /ar:ar-run, /ar:loop, /ar:ar-status, /ar:ar-resume), 8 built-in evaluators, configurable loop intervals (10min to monthly).

ponytail DietrichGebert ponytail steers Claude Code toward small, direct solutions and away from abstractions nobody asked for. Use it when you want the agent to build on what the project already has. ★ 176,443repo stars impeccable pbakaus Hands your agent a designer's vocabulary: 24 commands like polish, audit and bolder, so UI feedback stops being “make it pretty”. ★ 88,212repo stars last-30-days-skill mvanhorn Searches the web for what people posted about a topic in the last month and turns it into one structured brief. ★ 65,508repo stars claude-hud jarrodwatts Shows context usage, rate limits, running tools and todo progress under your input line. Useful when a session runs long and you want to watch the spend. ★ 28,841repo stars understand-anything Egonex-AI Turns codebases or markdown wikis into an interactive knowledge graph with a browser dashboard. Helps navigate unfamiliar repositories without reading files blindly. ★ 88,314repo stars mem0 mem0ai Adds persistent memory to Claude Code so your agent retains project context across terminal sessions. ★ 67,829repo stars

From the same set463

The whole set →