autoresearch: Instructions file for Claude Code

AGENTS.md

autoresearch AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from uditgoenka/autoresearch. It costs 2,635 tokens per session, scanned A, original, MIT.

Repository instructions for Autoresearch, a system that repeatedly changes a project, checks one measurable result, and keeps or discards each change.

In plain words
What is it for?
They help run repeated experiments on code, content, marketing, sales, or DevOps work when success can be measured.
Why use it?
They explain the iteration process and how to install it for coding agents such as Claude Code and Codex.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also the file is AGENTS.md. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Claude Code.

This is uditgoenka/autoresearch's own configuration. It tells Claude Code, Codex and OpenCode how to work on autoresearch itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything autoresearch configures →

About the project

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.

uditgoenka/autoresearch · 6,206 stars · on GitHub · udit.co

Reuse

Borrowing it

Nothing to install: this file belongs to uditgoenka/autoresearch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/uditgoenka/autoresearch/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/uditgoenka/autoresearch

Made for: Claude Code, Codex, OpenCode.

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 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/uditgoenka/autoresearch/agents-md.svg)](https://agentmods.dev/instructions/uditgoenka/autoresearch/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/uditgoenka/autoresearch/agents-md"><img src="https://agentmods.dev/badge/instructions/uditgoenka/autoresearch/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,635 This file is loaded in full into every session.
When invoked 2,635 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.02635 $0.02635
Opus 5 $0.01318 $0.01318
Sonnet 5 $0.00527 $0.00527
Haiku 4.5 $0.00264 $0.00264

Measured 8d ago against content hash 38b9b278ba12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

autoresearch AGENTS.md 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.

AGENTS.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Autoresearch

Drop this file into your project root. Any AI agent (Claude Code, Codex, OpenCode, Gemini CLI, etc.) can then use Autoresearch immediately.

What is Autoresearch?

Autonomous goal-directed iteration based on Karpathy's autoresearch. One metric, constrained scope, fast verification, automatic rollback, git as memory. Works on ANY domain — code, content, marketing, sales, DevOps — anything with a measurable metric.

Core loop: Modify → Verify → Keep/Discard → Repeat.


Installation

Claude Code (plugin)

/plugin marketplace add uditgoenka/autoresearch
/plugin install autoresearch@autoresearch

Restart session after install. All 14 commands become available as /autoresearch and /autoresearch:<subcommand>.

Codex (plugin)

git clone https://github.com/uditgoenka/autoresearch.git
cd autoresearch
./scripts/install.sh --codex --global

Invoke via the $autoresearch mention syntax: $autoresearch <subcommand> [flags].

Manual (any agent)

Copy the skill files into your agent's skill directory:

git clone https://github.com/uditgoenka/autoresearch.git

# Claude Code
cp -r autoresearch/claude-plugin/skills/autoresearch .claude/skills/autoresearch
cp -r autoresearch/claude-plugin/commands/autoresearch .claude/commands/autoresearch
cp autoresearch/claude-plugin/commands/autoresearch.md .claude/commands/autoresearch.md

# Codex
cp -r autoresearch/plugins/autoresearch ~/.agents/plugins/autoresearch

Commands

Command Purpose
autoresearch Autonomous iteration loop (unlimited or bounded with Iterations: N)
autoresearch:plan Interactive wizard: Goal → Scope, Metric, Direction, Verify config
autoresearch:debug Autonomous bug-hunting — scientific method + iterative investigation
autoresearch:fix Autonomous error repair — one fix per iteration until zero errors
autoresearch:security STRIDE + OWASP + red-team security audit (read-only unless --fix)
autoresearch:ship Universal shipping workflow — 8 phases, 9 shipment types
autoresearch:scenario Scenario exploration — 12 dimensions, edge cases, derivative scenarios
autoresearch:predict Multi-persona swarm — 5 expert perspectives before acting
autoresearch:learn Autonomous documentation engine — scout, generate, validate, fix
autoresearch:reason Adversarial refinement — blind judge panel for subjective domains
autoresearch:probe Adversarial requirement / assumption interrogation — 8 personas probe to mechanical saturation, emits ready-to-run autoresearch config

Read the full file on GitHub · 337 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. 8d ago First seen · 337 lines · 2,635 tokens per session scan A 38b9b278ba12

Subscribe to this mod's changes

autoresearch AGENTS.md is an instructions file published in the GitHub repository uditgoenka/autoresearch (6,206 stars, last pushed 25d ago), licensed MIT. It adds 2,635 tokens to every session, about $0.0132 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 instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens