autoresearch

autoresearch is a command for Claude Code from Maleick/AutoResearch. It costs 0 tokens per session (317 once invoked), scanned A, original, MIT.

A command that runs a structured improvement-and-check loop in OpenCode. It requires a goal, a measurable result, a direction for improvement, and a command that verifies each experiment.

In plain words
What is it for?
Use it to optimize code or other measurable outcomes through repeated focused changes, with commands for starting, checking, pausing, resuming, and completing a run.
Why use it?
It replaces informal trial and error with recorded experiments and mechanical checks. Regressions are discarded, while improvements are kept until the stop condition is reached.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions subagents; mentions OpenCode.

Good fit Use it to optimize code or other measurable outcomes through repeated focused changes, with commands for starting, checking, pausing, resuming, and completing a run.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/maleick/autoresearch/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.

Clone the repo
git clone --depth 1 https://github.com/Maleick/AutoResearch

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/commands/maleick/autoresearch/autoresearch/github.svg)](https://agentmods.dev/commands/maleick/autoresearch/autoresearch)
Your own site
<a href="https://agentmods.dev/commands/maleick/autoresearch/autoresearch"><img src="https://agentmods.dev/badge/commands/maleick/autoresearch/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/commands/maleick/autoresearch/autoresearch"><img src="https://agentmods.dev/badge/commands/maleick/autoresearch/autoresearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 317 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 $0.00000 $0.00317
Opus 5 $0.00000 $0.00159
Sonnet 5 $0.00000 $0.00063
Haiku 4.5 $0.00000 $0.00032

Measured 10d ago against content hash cb95269993ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 10d 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.

commands/autoresearch.md · 45 lines

What it actually says

/autoresearch

Run a subagent-first structured improve-verify loop in OpenCode.

Activation

  1. Read skills/autoresearch/references/loop-workflow.md
  2. Read skills/autoresearch/references/core-principles.md
  3. Read skills/autoresearch/references/state-management.md
  4. Read skills/autoresearch/references/results-logging.md
  5. For interactive setup, read skills/autoresearch/references/interaction-wizard.md

Required Fields

Collect these before launching:

  • Goal — What outcome should this run optimize?
  • Metric — What numeric metric tracks progress?
  • Directionlower or higher
  • Verify — The mechanical command that measures the metric

Execution Rules

  1. Baseline exactly once at run start.
  2. Make one focused experiment per iteration.
  3. Verify mechanically. Do not keep on intuition alone.
  4. Record every iteration before the next one starts.
  5. Keep strict improvements, discard regressions.
  6. Continue until the stop condition is met.

Background Control

autoresearch init --goal "..." --metric "..." --direction "lower" --verify "npm test"
autoresearch status
autoresearch stop
autoresearch resume
autoresearch complete

Output

Print a setup summary before the first iteration, progress updates during the loop, and a completion summary when done.

Follow skills/autoresearch/references/structured-output-spec.md for format.

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. 10d ago First seen · 45 lines · 0 tokens per session scan A cb95269993ce

Subscribe to this mod's changes

autoresearch is a command published in the GitHub repository Maleick/AutoResearch (10 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 317 tokens. 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.