agentmods.dev

autoresearch:reason

autoresearch:reason is a command for Claude Code from WdBlink/autoresearch-paper. It costs 14 tokens per session (1,224 once invoked), scanned A, a copy of autoresearch:reason, MIT.

A structured debate tool for refining a question, proposal, design, argument, or claim through independent judges and repeated rounds.

In plain words
What is it for?
Use it for software, product, business, security, research, or content decisions in convergent, creative, or debate-only modes.
Why use it?
It reduces reliance on one first impression by comparing competing views and stopping when the judgement converges.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: names the AskUserQuestion tool.

not rated 2repo 4d ago A scan 14 tokens copy · 94% MIT

Good fit Use it for software, product, business, security, research, or content decisions in convergent, creative, or debate-only modes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/wdblink/autoresearch-paper/reason
View source ↗ WdBlink/autoresearch-paper
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.

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:reason

README.md
[![agentmods](https://agentmods.dev/badge/commands/wdblink/autoresearch-paper/reason/github.svg)](https://agentmods.dev/commands/wdblink/autoresearch-paper/reason)
Your own site
<a href="https://agentmods.dev/commands/wdblink/autoresearch-paper/reason"><img src="https://agentmods.dev/badge/commands/wdblink/autoresearch-paper/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.

agentmods 80×15 button for autoresearch:reason

Your own site · 80×15
<a href="https://agentmods.dev/commands/wdblink/autoresearch-paper/reason"><img src="https://agentmods.dev/badge/commands/wdblink/autoresearch-paper/reason.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,224 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 94% 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00014 $0.01224
Opus 5.5 $0.00006 $0.00490
Sonnet 5.5 $0.00003 $0.00245
Haiku 4.5 $0.00001 $0.00122

Measured 3d ago against content hash e69b985c9489, 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

94% identical to autoresearch:reason — 0 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.

.claude/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)

AskUserQuestion (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

  1. Load references/reason-judge-protocol.md for judge and convergence specs
  2. Parse domain → select domain-specific judge criteria
  3. Create output directory: autoresearch/reason-{YYMMDD}-{HHMM}/
  4. TSV header: round\ttimestamp\tcandidate_label\tjudge_verdict\tconvergence_count\tdescription
  5. 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.

  1. 3d ago First seen · 111 lines · 14 tokens per session scan A e69b985c9489

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 14 tokens to every session and 1,224 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to autoresearch:reason, differing in 0 lines, and is treated as a copy.

PlanningResearchacademic-writingagent-skillsaiai-agentsautonomous-research
Related

autoresearch:reason compared with commands from other repositories

autoresearch:reason next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
autoresearch:reasonWdBlink/autoresearch-paperCommand24d agoMITA14Claude Code
ars-planImbad0202/academic-research-skillsCommand56kyesterdaynoneA19Claude Code
ars-revision-coachImbad0202/academic-research-skills-codexCommand14k5d agononeA27Claude Code
ars-3wImbad0202/academic-research-skills-codexCommand14k5d agononeA24Claude Code
nextProjectDXAI/labratCommand2373mo agoMITA0Claude Code
ja-fallbackZaious/journal-atlasCommand210d agononeA37Claude Code
ai-reviewStill-chowline394/MagicTeX-mcpCommand01mo agoAGPL-3.0A13Claude Code