autoresearch

autoresearch is a skill for Claude Code from CarbeneAI/Forge. It costs 120 tokens per session (1,200 once invoked), scanned A, original, MIT.

An autonomous research loop that repeatedly searches the web, reads sources, combines findings, and saves structured pages to a wiki.

In plain words
What is it for?
It helps investigate a topic through broad searches, targeted follow-up searches, source comparison, and structured knowledge-base pages.
Why use it?
It reduces the manual effort of collecting sources and organizing research into reusable notes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit It helps investigate a topic through broad searches, targeted follow-up searches, source comparison, and structured knowledge-base pages.

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

Made for: Claude Code.

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/carbeneai/forge/autoresearch/github.svg)](https://agentmods.dev/skills/carbeneai/forge/autoresearch)
Your own site
<a href="https://agentmods.dev/skills/carbeneai/forge/autoresearch"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/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/carbeneai/forge/autoresearch"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/autoresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,200 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 $0.00120 $0.01200
Opus 5 $0.00060 $0.00600
Sonnet 5 $0.00024 $0.00240
Haiku 4.5 $0.00012 $0.00120

Measured 6d ago against content hash 5c5ff6fd74f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 6d 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/skills/autoresearch/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

autoresearch: Autonomous Research Loop

You are a research agent. You take a topic, run iterative web searches, synthesize findings, and file everything into the wiki. The user gets wiki pages, not a chat response.

This is based on Karpathy's autoresearch pattern: a configurable program defines your objectives. You run the loop until depth is reached. Output goes into the knowledge base.


Before Starting

Read references/program.md to load the research objectives and constraints. This file is user-configurable. It defines what sources to prefer, how to score confidence, and any domain-specific constraints.


Research Loop

Input: topic (from user command)

Round 1. Broad search
1. Decompose topic into 3-5 distinct search angles
2. For each angle: run 2-3 WebSearch queries
3. For top 2-3 results per angle: WebFetch the page
4. Extract from each: key claims, entities, concepts, open questions

Round 2. Gap fill
5. Identify what's missing or contradicted from Round 1
6. Run targeted searches for each gap (max 5 queries)
7. Fetch top results for each gap

Round 3. Synthesis check (optional, if gaps remain)
8. If major contradictions or missing pieces still exist: one more targeted pass
9. Otherwise: proceed to filing

Max rounds: 3 (as set in program.md). Stop when depth is reached or max rounds hit.

Filing Results

After research is complete, create these pages:

wiki/sources/. One page per major reference found

  • Use source frontmatter (type, source_type, author, date_published, url, confidence, key_claims)
  • Body: summary of the source, what it contributes to the topic

wiki/concepts/. One page per significant concept extracted

  • Only create a page if the concept is substantive enough to stand alone
  • Check the index first: update existing concept pages rather than creating duplicates

wiki/entities/. One page per significant person, org, or product identified

  • Check the index first: update existing entity pages

wiki/questions/. One synthesis page titled "Research: [Topic]"

  • This is the master synthesis. Everything comes together here.
  • Sections: Overview, Key Findings, Entities, Concepts, Contradictions, Open Questions, Sources
  • Full frontmatter with related links to all pages created in this session

Read the full file on GitHub · 174 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. 6d ago First seen · 174 lines · 120 tokens per session scan A 5c5ff6fd74f3

Subscribe to this mod's changes

autoresearch is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 1,200 once invoked, about $0.0006 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

scanning-containers-with-trivy-in-cicd

This skill covers integrating Aqua Security's Trivy scanner into CI/CD pipelines for comprehensive container image vulnerability detection. It addresses scanning Docker images for OS package and application dependency CVEs, detecting misconfigurations in Dockerfiles, scanning filesystem and git repositories, and…

xalgorix/xalgorix · 74 tokens

implementing-code-signing-for-artifacts

This skill covers implementing code signing for build artifacts to ensure integrity and authenticity throughout the software supply chain. It addresses signing binaries, packages, and containers using GPG, Sigstore, and platform-specific signing tools, establishing trust chains, and verifying signatures in deployment…

xalgorix/xalgorix · 62 tokens

implementing-semgrep-for-custom-sast-rules

Write custom Semgrep SAST rules in YAML to detect application-specific vulnerabilities, enforce coding standards, and integrate into CI/CD pipelines.

xalgorix/xalgorix · 37 tokens

building-vulnerability-dashboard-with-defectdojo

Deploy DefectDojo as a centralized vulnerability management dashboard with scanner integrations, deduplication, metrics tracking, and Jira ticketing workflows.

26zl/cybersec-toolkit · 37 tokens

panguard

AI agent security platform — audit skills, scan for threats, and run 24/7 protection with 9,700+ detection rules.

panguard-ai/panguard-ai · 30 tokens

detecting-aws-credential-exposure-with-trufflehog

Detecting exposed AWS credentials in source code repositories, CI/CD pipelines, and configuration files using TruffleHog, git-secrets, and AWS-native detection mechanisms to prevent credential theft and unauthorized account access.

xalgorix/xalgorix · 54 tokens