autoresearch

autoresearch is a skill for Claude Code from naveedharri/benai-skills. It costs 59 tokens per session (5,525 once invoked), scanned A, original, MIT.

An automated loop that repeatedly changes a prompt, template, configuration, or code file and checks whether the result improves. It can use fixed checks or an AI judge with a scoring rubric.

In plain words
What is it for?
Use it to refine prompts, templates, settings, or code through repeated experiments, especially when you have tests or a clear quality score.
Why use it?
It removes the need to make and evaluate every small improvement manually when quality can be measured against defined criteria.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; names the AskUserQuestion tool.

Part of the all-skills plugin — 99 skills shipped together

Good fit Use it to refine prompts, templates, settings, or code through repeated experiments, especially when you have tests or a clear quality score.

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

Made for: Claude Code.

Or install all-skills, the plugin that ships this one along with the rest of its 99 skills.

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/naveedharri/benai-skills/autoresearch/github.svg)](https://agentmods.dev/skills/naveedharri/benai-skills/autoresearch)
Your own site
<a href="https://agentmods.dev/skills/naveedharri/benai-skills/autoresearch"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/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/naveedharri/benai-skills/autoresearch"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/autoresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,525 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: 1 finding, 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 Excessive Agency · line 285
    Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.
    Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
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 $0.00059 $0.05525
Opus 5 $0.00030 $0.02763
Sonnet 5 $0.00012 $0.01105
Haiku 4.5 $0.00006 $0.00553

Measured 12d ago against content hash ff535f465e70, 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (references/example-eval.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/all-skills/skills/autoresearch/SKILL.md · 458 lines

How it starts

The opening of the file, as written. The whole thing — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AutoResearch — Autonomous Optimization Loop

USE WHEN the user runs /autoresearch, says "autoresearch", "optimize this prompt", "improve this overnight", "run an optimization loop", "iterate on this", "auto-improve", or wants to autonomously refine a file against measurable criteria.


Architecture: Separation of Roles

This skill supports two mutually exclusive evaluation modes. Both maintain four-way separation.

Deterministic Mode (default) — Four-Way Separation

Role Who Knows Eval Code? Knows Prompt History?
Main Agent You (optimizer) NO — reads metric number only Yes — reads logs, plans changes
Eval Agent autoresearch-eval-agent sub-agent Yes — writes eval.py No
Test Runner autoresearch-test-runner sub-agent NO — fresh context NO
Judge Script eval.py (deterministic Python) IS the eval No

Metric: pass_rate. Best for tasks with clear, mechanical quality checks (word count, format, keywords, structure).

AI Judge Mode (opt-in) — Four-Way Separation

Role Who Knows Rubric? Knows Prompt History?
Main Agent You (optimizer) Criteria names only Yes — reads logs, plans changes
Eval Agent autoresearch-eval-agent sub-agent Yes — writes rubric.md No
Test Runner autoresearch-test-runner sub-agent NO — fresh context NO
Judge Agent autoresearch-judge sub-agent Follows rubric NO — fresh context

Metric: quality_score. Best for creative/subjective tasks where mechanical checks miss the point (tone, authenticity, narrative, emotional resonance).

The modes are mutually exclusive. Deterministic mode uses eval.py only. AI judge mode uses the judge agent only. There is no combined score.

Key isolation (both modes):

  • The optimizer never writes eval artifacts, never generates outputs
  • The eval agent writes the eval system once (eval.py OR rubric.md), then disappears
  • The test runner never sees the eval or rubric — fresh context every time
  • The judge (script or agent) evaluates without knowing iteration history or optimizer intent

Read the full file on GitHub · 458 lines

Files

What ships with it

4 files 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. 12d ago First seen · 458 lines · 59 tokens per session scan A ff535f465e70

Subscribe to this mod's changes

autoresearch is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed 8d ago), licensed MIT. It adds 59 tokens to every session and 5,525 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.

Related

Other skills, from other repositories

evaluating-llms-harness

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

NousResearch/hermes-agent · 29 tokens

cli-eval

Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.

diegosouzapw/OmniRoute · 34 tokens

model-merging

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…

davila7/claude-code-templates · 73 tokens

data-quality-frameworks

Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.

wshobson/agents · 37 tokens

dbt-transformation-patterns

Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best practices.

wshobson/agents · 47 tokens

darwinian-evolver

Evolve prompts/regex/SQL/code with Imbue's evolution loop.

NousResearch/hermes-agent · 22 tokens