autoresearch

autoresearch is a skill for Claude Code from ehmo/autoresearch-skill. It costs 26 tokens per session (6,987 once invoked), scanned A, original, MIT.

An autonomous system for improving a codebase through repeated work cycles run by up to three teams. It supports narrow work toward a specific measurable goal and broad exploration of different improvement ideas.

In plain words
What is it for?
It is for pursuing a defined codebase improvement, exploring several possible approaches, coordinating teams, and checking whether changes meet their goals.
Why use it?
It organizes parallel improvement efforts and keeps track of handoffs, information sharing, tests, and results.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md; mentions subagents; positional $N argument.

Good fit It is for pursuing a defined codebase improvement, exploring several possible approaches, coordinating teams, and checking whether changes meet their goals.

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

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/ehmo/autoresearch-skill/autoresearch/github.svg)](https://agentmods.dev/skills/ehmo/autoresearch-skill/autoresearch)
Your own site
<a href="https://agentmods.dev/skills/ehmo/autoresearch-skill/autoresearch"><img src="https://agentmods.dev/badge/skills/ehmo/autoresearch-skill/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/ehmo/autoresearch-skill/autoresearch"><img src="https://agentmods.dev/badge/skills/ehmo/autoresearch-skill/autoresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,987 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 $0.06987
Opus 5 $0.00013 $0.03494
Sonnet 5 $0.00005 $0.01397
Haiku 4.5 $0.00003 $0.00699

Measured 9d ago against content hash 49a8cb301484, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 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.

skills/autoresearch/SKILL.md · 564 lines

How it starts

The opening of the file, as written. The whole thing — 564 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autoresearch

Current version: 2.0.0 (semver). Changelog: skills/autoresearch/CHANGELOG.md.

Version scheme:

  • MAJOR — protocol-breaking changes (new modes, incompatible session layout, changed team contract).
  • MINOR — new features that existing sessions can ignore without breaking.
  • PATCH — wording fixes, bug fixes, clarifications.

When you start a new session, stamp the skill version into session.md (field: Skill version). When resuming, read that stamp and compare to the current version — if they differ, note the delta to the user and continue with the newer version unless the change was MAJOR (in which case warn and ask).

You coordinate an autonomous codebase improvement system. Up to three teams run in cycles against a target codebase. You manage handoffs, control information flow, verify tests, and log results.

Autoresearch has three execution modes:

  • narrow — the user has a specific measurable goal. You work priority-ranked angles in order until the goal is met or exhausted.
  • broad — the user has an aspiration. You generate 3–5 categorically-diverse hypotheses (obvious + bold + creative at minimum) and run each on its own independent track, then compare.
  • sweep (default when no mode is specified) — general quality improvement with no specific target. Cycles of Red → Green → Refactor until diminishing returns.

Clean-room information barriers between Red, Green, and Refactor teams apply in all three modes.


Parse arguments

From $ARGUMENTS:

  • narrow <path> → narrow mode, new session on that codebase
  • broad <path> → broad mode, new session on that codebase
  • A bare filesystem path = sweep mode, new session
  • resume = continue the most recent session (mode is read from session.md)
  • resume <name> = continue a named session
  • status = print progress summary and stop
  • version = print the current skill version (from frontmatter) and stop

If no arguments or unrecognized input, print usage and stop:

Usage: /autoresearch narrow <path>  Drive a specific measurable goal
       /autoresearch broad <path>   Explore 3–5 diverse hypotheses
       /autoresearch <path>         General quality sweep (legacy)
       /autoresearch resume         Continue last session
       /autoresearch status         Show progress
       /autoresearch version        Print skill version

Read the full file on GitHub · 564 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. 9d ago First seen · 564 lines · 26 tokens per session scan A 49a8cb301484

Subscribe to this mod's changes

autoresearch is a skill published in the GitHub repository ehmo/autoresearch-skill (53 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 6,987 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.