autoresearch is an agent workflow that repeatedly changes a project, verifies a measurable result, keeps or discards the change, and continues iterating toward a goal. It is for autonomous improvement tasks in Claude Code, OpenCode, and OpenAI Codex across domains with mechanical success measures. The catalogue contains its commands, hooks, skills, plugin, agent, and instruction.
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.
git clone --depth 1 https://github.com/uditgoenka/autoresearchWrote 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.
[](https://agentmods.dev/plugins/uditgoenka/autoresearch/claude-plugin)<a href="https://agentmods.dev/plugins/uditgoenka/autoresearch/claude-plugin"><img src="https://agentmods.dev/badge/plugins/uditgoenka/autoresearch/claude-plugin/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.
<a href="https://agentmods.dev/plugins/uditgoenka/autoresearch/claude-plugin"><img src="https://agentmods.dev/badge/plugins/uditgoenka/autoresearch/claude-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
claude-plugin 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- autoresearch — 86% identical, 7 lines differ
What it actually says
{
"name": "autoresearch",
"description": "Autonomous improvement engine. 14 commands: iterate, plan, debug, fix, security, ship, scenario, predict, learn, reason, probe, improve, evals, regression.",
"version": "2.2.2",
"author": {
"name": "Udit Goenka",
"url": "https://github.com/uditgoenka"
},
"repository": "https://github.com/uditgoenka/autoresearch",
"license": "MIT",
"homepage": "https://github.com/uditgoenka/autoresearch",
"keywords": [
"autonomous",
"iteration",
"optimization",
"debugging",
"security-audit",
"shipping",
"evals"
]
}
What it installs
The manifest is a name and a version. 5 hooks travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago First seen · 22 lines scan A 49c159a5c41b
claude-plugin is a plugin published in the GitHub repository uditgoenka/autoresearch (6,577 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
coral
Author and run CORAL tasks from your own harness. Teaches the coral CLI workflow (init/validate, start/status/resume/log/show) and checks coral is installed on session start.
research-git
A memory system for the code you're exploring: capture each idea as a semantic Feature Capsule, recall it, and regenerate it onto today's codebase. Segmentation/regeneration run on natively-dispatched subagents (your subscription) — no pay-per-use API. MCP serves the graph read-only for sharing.
ooda-loop marketplace
Plugin marketplace listing 1 plugin: ooda-loop.
openclaw-cc
Autonomous AI assistant with 3-tier persistent memory, knowledge graph, 21 workflow skills, and multi-agent orchestration via Discord/Telegram.
claude-code-autoresearch
Autonomous experiment loop for Claude Code — run, measure, keep or discard. Ruby port of davebcn87/pi-autoresearch.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.