autoresearch

autoresearch is an agent for Claude Code from agencia-conversion/agentic-seo-skills. It costs 26 tokens per session (291 once invoked), scanned A, original, MIT.

An automated research loop for improving coding-agent skills and related test fixtures. It measures results, records experiments, and decides whether changes should be kept or rejected.

In plain words
What is it for?
Use it to run skill evaluations, set baselines, record iterations, audit skill quality, validate files, and produce a final experiment report.
Why use it?
It gives skill development a repeatable way to compare changes and catch regressions, meaning cases where an improvement breaks existing behavior.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/autoresearch.mjs init --problem "<...>" --mode skill-eval --max-iter 6.

Part of the agentic-seo plugin — 21 skills, 2 commands, 13 agents, 3 hooks shipped together

Good fit Use it to run skill evaluations, set baselines, record iterations, audit skill quality, validate files, and produce a final experiment report.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/agencia-conversion/agentic-seo-skills
agentmods
npx agentmods add agents/agencia-conversion/agentic-seo-skills/autoresearch

Made for: Claude Code.

Or install agentic-seo, the plugin that ships this one along with the rest of its 21 skills, 2 commands, 13 agents, 3 hooks.

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/agents/agencia-conversion/agentic-seo-skills/autoresearch/github.svg)](https://agentmods.dev/agents/agencia-conversion/agentic-seo-skills/autoresearch)
Your own site
<a href="https://agentmods.dev/agents/agencia-conversion/agentic-seo-skills/autoresearch"><img src="https://agentmods.dev/badge/agents/agencia-conversion/agentic-seo-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/agents/agencia-conversion/agentic-seo-skills/autoresearch"><img src="https://agentmods.dev/badge/agents/agencia-conversion/agentic-seo-skills/autoresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 291 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.
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 $0.00026 $0.00291
Opus 5 $0.00013 $0.00146
Sonnet 5 $0.00005 $0.00058
Haiku 4.5 $0.00003 $0.00029

Measured 12d ago against content hash 53fcee4ad37e, 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.

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/autoresearch.md · 25 lines

What it actually says

You are the Agentic SEO Autoresearch sub-agent.

Use program.md as the operating protocol — it defines the editable surface, the immutable surface, and the experiment-loop contract for plugin development.

Use scripts/autoresearch.mjs as the engine that persists state, decides stops, and writes the journal. Subcommands: init, frame-metrics, commit-metrics, set-baseline, record, finalize, resume, report. The full schema lives in skills/_shared/references/autoresearch-protocol.md.

Use bin/agentic-seo audit-skills for one-shot quality scoring of all skills (frontmatter + Contract + Required Behavior + Done Criteria + shared reference). Run before and after each iteration.

Prefer:

node scripts/autoresearch.mjs init --problem "<...>" --mode skill-eval --max-iter 6
node scripts/validate_skills.mjs
bin/agentic-seo audit-skills
claude plugin validate .

Evaluate one skill or subsystem at a time. Keep changes only when deterministic checks pass and quality improves without weakening decision/check gates or provenance.

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 · 25 lines · 26 tokens per session scan A 53fcee4ad37e

Subscribe to this mod's changes

autoresearch is an agent published in the GitHub repository agencia-conversion/agentic-seo-skills (51 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 291 once invoked, about $0.0001 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.