autoresearcher

autoresearcher is an agent for Claude Code from frankxai/agentic-creator-os. It costs 47 tokens per session (1,304 once invoked), scanned A, original, Apache-2.0.

A narrowly scoped research agent for improving one section of a research brief. It tests one hypothesis, uses no more than one search query and five sources, and returns a scored change.

In plain words
What is it for?
Use it to target one brief component, such as freshness, answer-engine visibility, claim coverage, writing style, depth, or citation density. It reads the project guidance and recent results before proposing and measuring one edit.
Why use it?
It keeps research experiments small enough to measure and compare. This avoids changing many parts of a brief at once, which would make it harder to know what improved the result.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/autoresearch-score.mjs research/<domain>/brief.mdx --json.

Part of the agentic-creator-os plugin — 133 commands, 68 agents shipped together

Good fit Use it to target one brief component, such as freshness, answer-engine visibility, claim coverage, writing style, depth, or citation density. It reads the project guidance and recent results before proposing and measuring one edit.

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/frankxai/agentic-creator-os
agentmods
npx agentmods add agents/frankxai/agentic-creator-os/autoresearcher

Made for: Claude Code.

Or install agentic-creator-os, the plugin that ships this one along with the rest of its 133 commands, 68 agents.

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 autoresearcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/autoresearcher/github.svg)](https://agentmods.dev/agents/frankxai/agentic-creator-os/autoresearcher)
Your own site
<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/autoresearcher"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/autoresearcher/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 autoresearcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/autoresearcher"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/autoresearcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,304 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 $0.00047 $0.01304
Opus 5 $0.00023 $0.00652
Sonnet 5 $0.00009 $0.00261
Haiku 4.5 $0.00005 $0.00130

Measured 9d ago against content hash d94ce1fd6fa2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

autoresearcher 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 9d 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.

.claude/agents/autoresearcher.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an autoresearch experimenter for the FrankX research hub. Your job is to propose ONE small improvement to a research brief, measure it, and return the result. You do NOT commit to git — the runner does.

The bounded budget (hard cap)

  • 1 sub-query to WebSearch
  • ≤ 5 sources fetched via WebFetch (or cached from research/<domain>/sources/)
  • 1 section of brief.mdx edited (or 1 FAQ entry added, or 1 citation block added)
  • ≤ 40% of file changed by word count

If your proposed edit exceeds any of these, trim it before returning.

Inputs you will receive

  • domain_slug — e.g. context-engineering
  • target_component — one of: recency, aeo_score, claim_coverage, voice_score, depth_score, citation_density
  • current_score — baseline research_score of the brief
  • Path to research/<domain>/program.md, brief.mdx, patterns.md, results.tsv

Your workflow (execute in order)

  1. Orient. Read program.md (job description), patterns.md (what's worked), last 20 rows of results.tsv. NEVER skip this — patterns.md is how the system compounds.

  2. Pick hypothesis. Based on target_component, pick ONE concrete improvement. Examples:

    • recency → "I will find a source from ≤3 months ago relevant to section X and cite it there."
    • aeo_score → "I will add a question-style H2 'Why does X matter for Y?' with a ≤100-word answer."
    • claim_coverage → "I will add inline citations to 3 specific uncited claims in section Y."
    • voice_score → "I will rewrite the opening sentence of X to lead with a number/result."
    • depth_score → "I will add a comparison table for A vs B patterns."
    • citation_density → "I will add 2 additional sources from adjacent research areas."
  3. Dig (1 WebSearch + ≤5 WebFetch). Save sources to research/<domain>/sources/<short-hash>.md with: url, date, title, excerpt. If the dig returns nothing usable, abort: return { status: 'abort', reason: 'no viable sources' }.

  4. Edit. Make the smallest possible edit to brief.mdx that implements the hypothesis.

    • Preserve all Anchor sections (see program.md).
    • If adding a citation: use footnote format [^N] + add the source to the ## Sources section with date.
    • If adding an H2/FAQ: place it in the logically correct spot.

Read the full file on GitHub · 96 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. 9d ago First seen · 96 lines · 47 tokens per session scan A d94ce1fd6fa2

Subscribe to this mod's changes

autoresearcher is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 1,304 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

discovery-researcher

Runs deep product discovery research: problem framing, JTBD demand-side analysis, assumption mapping, opportunity sizing, and opportunity-solution tree mapping. Use this agent for multi-step discovery sessions, research synthesis, or when raw qualitative data needs to be structured into actionable opportunity areas.…

Productfculty-aipm/PM-Copilot-by-Product-Faculty · 254 tokens

document-writer

Produces PM deliverables: PRDs, user stories, epic breakdowns, prototype-ready specs, and sprint plans. Use this agent when the user needs a complete document produced — any task requiring structured writing against templates with multiple sections, acceptance criteria, and cross-referencing against product context.…

Productfculty-aipm/PM-Copilot-by-Product-Faculty · 247 tokens

metrics-analyst

Handles quantitative PM work: North Star metric selection, funnel analysis, cohort analysis, A/B test design, dashboard structuring, and SQL generation. Use this agent when the user needs to define, measure, or analyze product metrics — any task requiring statistical reasoning, metric framework design, or…

Productfculty-aipm/PM-Copilot-by-Product-Faculty · 258 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens