What is autoresearch_reason?

A structured debate tool for questions, proposals, designs, arguments, or claims. Several blind judges review the topic through repeated rounds until the results converge, meaning the same option keeps winning.

Use it to refine software designs, product decisions, business choices, security questions, research claims, or written content. It supports convergent refinement, creative exploration, and debate without a final synthesis.

It exposes weak assumptions and competing viewpoints before a decision is made. The repeated independent reviews can make reasoning less dependent on one initial answer.

autoresearch_reason — Command for Claude Code and OpenCode by WdBlink

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/WdBlink/autoresearch-paper

Made for: Claude Code, OpenCode.

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/commands/wdblink/autoresearch-paper/autoresearch_reason/github.svg)](https://agentmods.dev/commands/wdblink/autoresearch-paper/autoresearch_reason)

Your own site

<a href="https://agentmods.dev/commands/wdblink/autoresearch-paper/autoresearch_reason"><img src="https://agentmods.dev/badge/commands/wdblink/autoresearch-paper/autoresearch_reason/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/commands/wdblink/autoresearch-paper/autoresearch_reason"><img src="https://agentmods.dev/badge/commands/wdblink/autoresearch-paper/autoresearch_reason.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,221 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 91% copy Near-identical to another mod 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	$0.00013	$0.01221
Opus 5.5	$0.00005	$0.00488
Sonnet 5.5	$0.00003	$0.00244
Haiku 4.5	$0.00001	$0.00122

Measured 3d ago against content hash e3f12422abcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

autoresearch_reason 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.

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.

Origin

This is a copy

91% identical to autoresearch:reason — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.opencode/commands/autoresearch_reason.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EXECUTE IMMEDIATELY.

Parse Arguments

Extract from $ARGUMENTS:

Task: — question, proposal, design, argument, or claim to refine
Domain: or --domain — software, product, business, security, research, content
Mode: or --mode — convergent (default), creative, debate
--judges N or Judges: — blind judge count (3 default, 5 thorough, 7 deep)
--convergence N or Convergence: — stop when incumbent wins N consecutive rounds (default 3)
Iterations: or --iterations — default 8. "unlimited" for unbounded.
--judge-personas — custom judge persona overrides
--no-synthesis — skip synthesis, pure debate only
--temperature — generation temperature hint
--evals, --evals-interval N, --chain, --<subcommand>

Remaining text not matching flags = task description.

Setup (if Task or Domain missing)

question (single batch): Q1 (Task): "What should be reasoned about?" — open text Q2 (Domain): "What domain?" — software architecture, product strategy, business decision, security, research, content Q3 (Mode): "Refinement mode?" — convergent (stop when winner repeats), creative (never auto-stop), debate (no synthesis) Q4 (Judges): "How many blind judges?" — 3 (default), 5 (thorough), 7 (deep) If all provided → skip.

Setup Phase

Load references/reason-judge-protocol.md for judge and convergence specs
Parse domain → select domain-specific judge criteria
Create output directory: autoresearch/reason-{YYMMDD}-{HHMM}/
TSV header: round\ttimestamp\tcandidate_label\tjudge_verdict\tconvergence_count\tdescription
Initialize: incumbent = null, convergence_count = 0

Round Loop

Phase 1: Generate-A

If round 1: Author-A generates first candidate from task description
If round N>1: incumbent is Author-A's candidate
Cold-start: Author-A sees ONLY task description + domain context

Phase 2: Critic

Critic receives candidate-A (cold-start, no shared session)
MUST find at least 3 specific weaknesses
MUST suggest what a superior candidate would do differently
Role is purely adversarial — never compliment

Read the full file on GitHub · 111 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.

3d ago First seen · 111 lines · 13 tokens per session scan A e3f12422abcc

Subscribe to this mod's changes

autoresearch_reason is a command published in the GitHub repository WdBlink/autoresearch-paper (2 stars, last pushed 4d ago), licensed MIT. It adds 13 tokens to every session and 1,221 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to autoresearch:reason, differing in 4 lines, and is treated as a copy.

Planning Research academic-writing agent-skills ai ai-agents autonomous-research

autoresearch_reason next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
autoresearch_reasonWdBlink/autoresearch-paper	Command	2	4d ago	MIT	A	13	Claude Code, OpenCode
ars-planImbad0202/academic-research-skills	Command	56k	yesterday	none	A	19	Claude Code
ars-revision-coachImbad0202/academic-research-skills-codex	Command	14k	5d ago	none	A	27	Claude Code
ars-3wImbad0202/academic-research-skills-codex	Command	14k	5d ago	none	A	24	Claude Code
nextProjectDXAI/labrat	Command	237	3mo ago	MIT	A	0	Claude Code
ja-fallbackZaious/journal-atlas	Command	2	10d ago	none	A	37	Claude Code
ai-reviewStill-chowline394/MagicTeX-mcp	Command	0	1mo ago	AGPL-3.0	A	13	Claude Code