What is autoresearch?

An autonomous experiment loop that repeatedly tests changes against an optimization target. It records experiments, results, and checkpoints so the work can continue across turns until a configured limit or target is reached.

Use it to set up and run repeated optimization experiments with an objective, configuration limits, an experiment log, and a worklog.

It prevents promising ideas from being lost and provides a mechanism for continuing trials without manually restarting the process each time.

autoresearch — Skill for Claude Code by drivelineresearch

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 drivelineresearch/autoresearch-claude-code --skill autoresearch

Clone the repo

git clone --depth 1 https://github.com/drivelineresearch/autoresearch-claude-code

Made for: Claude Code.

Or install autoresearch, the plugin that ships this one along with the rest of its 1 skill, 1 command, 4 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/drivelineresearch/autoresearch-claude-code/autoresearch/github.svg)](https://agentmods.dev/skills/drivelineresearch/autoresearch-claude-code/autoresearch)

Your own site

<a href="https://agentmods.dev/skills/drivelineresearch/autoresearch-claude-code/autoresearch"><img src="https://agentmods.dev/badge/skills/drivelineresearch/autoresearch-claude-code/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/drivelineresearch/autoresearch-claude-code/autoresearch"><img src="https://agentmods.dev/badge/skills/drivelineresearch/autoresearch-claude-code/autoresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,423 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.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.02423
Opus 5	$0.00024	$0.01211
Sonnet 5	$0.00010	$0.00485
Haiku 4.5	$0.00005	$0.00242

Measured 3d ago against content hash 70951fb6f058, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 3d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/ar_state.py, scripts/ar-log.sh, scripts/codex_loop.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.

skills/autoresearch/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autoresearch

Try a scoped change, measure it against a fixed benchmark, keep a supported improvement, and record what happened. Continue within the user's authorization and a finite budget. User interruptions and scope changes take precedence over continuation instructions.

Host and mode

Resolve AR_SCRIPTS to the scripts directory alongside this skill's actual file. The helpers require Python 3.10+; Bash wrappers and locking support Linux/macOS.

Claude Code: invoke /autoresearch for manual installation, or /autoresearch:autoresearch when loaded as a plugin. The four registered Claude hooks handle continuation and compaction. Complete one experiment per turn.
Codex: invoke $autoresearch in CLI/IDE, or select this skill in the app. Use the same protocol with Codex's available read/edit/exec tools. This package's Claude hook registration does not install Codex hooks. For unattended continuation, use scripts/codex_loop.py as described in references/codex.md. A supervisor turn must complete exactly one experiment and then end. Never nest a supervisor inside a supervised turn.
Status: read state/dashboard/worklog and report; run no experiments and do not unpause. python3 "$AR_SCRIPTS/ar_state.py" status is a read-only status command.
Report: write autoresearch-report.md with objective, baseline, best, winning changes, evidence limitations, failures, and remaining ideas; run no experiments.
Off/pause: create .autoresearch-off and stop. During a running benchmark, cancel safely if possible; preserve partial work and report any unfinished process.

For Claude status/report turns in an active experiment, first create .autoresearch-inspect in the experiment workspace, including when this skill was loaded directly. The Stop hook consumes it to let the inspection turn end. For status, this control-file write is the only write; it does not log or run an experiment. Codex status remains read-only and creates no inspection sentinel.

Read the full file on GitHub · 187 lines

Files

What ships with it

5 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.

3d ago Changed · -148 lines · +3 tokens per session scan B → A 70951fb6f058
12d ago First seen · 335 lines · 46 tokens per session scan B e22bdcc20d84

Subscribe to this mod's changes

autoresearch is a skill published in the GitHub repository drivelineresearch/autoresearch-claude-code (343 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 2,423 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 2026-08-30.

Scientific

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens