autoresearch

autoresearch is a skill for Claude Code, Codex from adriannoes/awesome-agentic-ai. It costs 100 tokens per session (3,853 once invoked), scanned A, original, MIT.

A method for improving a Claude Code skill by running it repeatedly against test inputs, scoring the results with yes-or-no checks, and changing the instructions based on failures.

In plain words
What is it for?
Use it to optimize a skill, keep successful instruction changes, record attempted mutations, and review the resulting score history and changelog.
Why use it?
Skill behavior can be inconsistent, and manual improvements may miss recurring mistakes. Repeated evaluation shows whether a prompt change actually improves its results.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions Claude Code.

Good fit Use it to optimize a skill, keep successful instruction changes, record attempted mutations, and review the resulting score history and changelog.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adriannoes/awesome-agentic-ai/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 adriannoes/awesome-agentic-ai --skill autoresearch
Clone the repo
git clone --depth 1 https://github.com/adriannoes/awesome-agentic-ai

Made for: Claude Code, Codex.

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/adriannoes/awesome-agentic-ai/autoresearch/github.svg)](https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/autoresearch)
Your own site
<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/autoresearch"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/autoresearch/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 autoresearch

Your own site · 80×15
<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/autoresearch"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/autoresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,853 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: 2 findings, up to medium

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 →

  • medium Rogue Agent · line 8
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Agent Snooping · line 268
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00100 $0.03853
Opus 5 $0.00050 $0.01927
Sonnet 5 $0.00020 $0.00771
Haiku 4.5 $0.00010 $0.00385

Measured 7d ago against content hash 24c775cbca93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 7d 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.

cursor-claude-codex/skills/autoresearch/SKILL.md · 332 lines

How it starts

The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autoresearch for Skills

Most skills work about 70% of the time. The other 30% you get garbage. The fix isn't to rewrite the skill from scratch. It's to let an agent run it dozens of times, score every output, and tighten the prompt until that 30% disappears.

This skill adapts Andrej Karpathy's autoresearch methodology (autonomous experimentation loops) to Claude Code skills. Instead of optimizing ML training code, we optimize skill prompts.


the core job

Take any existing skill, define what "good output" looks like as binary yes/no checks, then run an autonomous loop that:

  1. Generates outputs from the skill using test inputs
  2. Scores every output against the eval criteria
  3. Mutates the skill prompt to fix failures
  4. Keeps mutations that improve the score, discards the rest
  5. Repeats until the score ceiling is hit or the user stops it

Output: An improved SKILL.md + results.tsv log + changelog.md of every mutation attempted + a live HTML dashboard you can watch in your browser.


before starting: gather context

STOP. Do not run any experiments until all fields below are confirmed with the user. Ask for any missing fields before proceeding.

  1. Target skill — Which skill do you want to optimize? (need the exact path to SKILL.md)
  2. Test inputs — What 3-5 different prompts/scenarios should we test the skill with? (variety matters — pick inputs that cover different use cases so we don't overfit to one scenario)
  3. Eval criteria — What 3-6 binary yes/no checks define a good output? (these are your "test questions" — see references/eval-guide.md for how to write good evals)
  4. Runs per experiment — How many times should we run the skill per mutation? Default: 5. (more runs = more reliable scores, but slower and more expensive. 5 is the sweet spot for most skills.)
  5. Run interval — How often should experiments cycle? Default: every 2 minutes. (shorter = faster iteration, but costs more)
  6. Budget cap — Optional. Max number of experiment cycles before stopping. Default: no cap (runs until you stop it).

Read the full file on GitHub · 332 lines

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. 7d ago First seen · 332 lines · 100 tokens per session scan A 24c775cbca93

Subscribe to this mod's changes

autoresearch is a skill published in the GitHub repository adriannoes/awesome-agentic-ai (57 stars, last pushed 13d ago), licensed MIT. It adds 100 tokens to every session and 3,853 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 2026-09-03.

Related

Other skills, from other repositories

java-unit-test

A code-generation guide for Java unit tests in Spring Boot projects. Unit tests check one small piece of code in isolation; Spring Boot is a Java framework for building web applications and services.

hashgraph-online/awesome-codex-plugins · 113 tokens

running-julia-test

Before running tests for a new package, make sure the test environment is already set up. If the package does not have tests yet, follow creating-julia-test-env first. Tests that use using Test must have Test available from the package or test project.

hashgraph-online/awesome-codex-plugins · 10 tokens

agent-debug-fixer

A Chinese-language debugging and repair workflow for software problems. It investigates errors, failed tests, broken pages, or behavior that does not match expectations, then makes a minimal fix.

hashgraph-online/awesome-codex-plugins · 71 tokens

design-qa-checklist

Build a QA checklist for verifying that a build matches the design. Use at implementation review. For the spec engineers build from, use handoff-spec.

Owl-Listener/designer-skills · 37 tokens

testing

Use this skill when writing, reviewing, or improving tests in WrongStack. Triggers: user says "test", "unit test", "integration test", "e2e", "mock", "vitest", "coverage", "assert", "expect", "test strategy", "write tests".

WrongStack/WrongStack · 61 tokens

reviewing-changes

Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.

JetBrains/thinkrail · 59 tokens