autor.research-pipeline

autor.research-pipeline is a command for Claude Code from llv22/AutoResearchWithEyes. It costs 83 tokens per session (1,580 once invoked), scanned A, original, MIT.

An end-to-end research workflow that moves from a broad idea to experiments and externally reviewed research.

In plain words
What is it for?
Use it to find and rank research ideas, run pilot experiments, implement the chosen direction, and review the results. It does not write the final paper.
Why use it?
It joins idea discovery, implementation, testing, and review so these stages do not have to be coordinated manually.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions Claude Code.

Part of the auto-research-with-eyes plugin — 10 skills, 5 commands, 2 agents, 1 MCP server shipped together

Good fit Use it to find and rank research ideas, run pilot experiments, implement the chosen direction, and review the results. It does not write the final paper.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/llv22/autoresearchwitheyes/autor.research-pipeline
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/llv22/AutoResearchWithEyes

Made for: Claude Code.

Or install auto-research-with-eyes, the plugin that ships this one along with the rest of its 10 skills, 5 commands, 2 agents, 1 MCP server.

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 autor.research-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/commands/llv22/autoresearchwitheyes/autor.research-pipeline/github.svg)](https://agentmods.dev/commands/llv22/autoresearchwitheyes/autor.research-pipeline)
Your own site
<a href="https://agentmods.dev/commands/llv22/autoresearchwitheyes/autor.research-pipeline"><img src="https://agentmods.dev/badge/commands/llv22/autoresearchwitheyes/autor.research-pipeline/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 autor.research-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/commands/llv22/autoresearchwitheyes/autor.research-pipeline"><img src="https://agentmods.dev/badge/commands/llv22/autoresearchwitheyes/autor.research-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,580 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 $0.00083 $0.01580
Opus 5 $0.00042 $0.00790
Sonnet 5 $0.00017 $0.00316
Haiku 4.5 $0.00008 $0.00158

Measured 9d ago against content hash 9f226bdc7d6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

autor.research-pipeline 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.

commands/autor.research-pipeline.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Full Research Pipeline: Idea → Experiments → Reviewed Research

End-to-end autonomous research workflow for: $ARGUMENTS

Constants

All constants (PILOT_MAX_HOURS, MAX_ROUNDS, POSITIVE_THRESHOLD, REVIEWER_MODEL) are defined in the project's CLAUDE.md. Read them from there before proceeding.

Overview

This skill chains two major workflows plus the implementation bridge between them:

/autor.idea-discovery → implement → /run-experiment → /autor.auto-review-loop → reviewed research
├── Workflow 1 ──┤            ├────────── Workflow 2 ──────────────┤

Note: This pipeline ends at reviewed research. To generate a submission-ready PDF, run /autor.paper-writing separately after this completes.

Pipeline

Stage 1: Idea Discovery (Workflow 1)

Invoke the idea discovery pipeline:

/autor.idea-discovery "$ARGUMENTS"

This internally runs: /research-lit/idea-creator/novelty-checkresearch-reviewer agent

Output: IDEA_REPORT.md with ranked, validated, pilot-tested ideas.

Gate 1 — Human Checkpoint:

After IDEA_REPORT.md is generated, pause and present the top ideas to the user:

Idea Discovery complete. Top ideas:

1. [Idea 1 title] — Pilot: POSITIVE (+X%), Novelty: CONFIRMED
2. [Idea 2 title] — Pilot: WEAK POSITIVE (+Y%), Novelty: CONFIRMED
3. [Idea 3 title] — Pilot: NEGATIVE, eliminated

Recommended: Idea 1. Shall I proceed with implementation?

Wait for user confirmation before continuing. The user may:

  • Approve an idea → proceed to Stage 2.
  • Pick a different idea → proceed with their choice.
  • Request changes (e.g., "combine Idea 1 and 3", "focus more on X") → update the idea prompt with user feedback, re-run /autor.idea-discovery with refined constraints, and present again.
  • Reject all ideas → collect feedback on what's missing, re-run Stage 1 with adjusted research direction. Repeat until the user commits to an idea.
  • Stop here → save current state to IDEA_REPORT.md for future reference.

Read the full file on GitHub · 167 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. 9d ago First seen · 167 lines · 83 tokens per session scan A 9f226bdc7d6e

Subscribe to this mod's changes

autor.research-pipeline is a command published in the GitHub repository llv22/AutoResearchWithEyes (5 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,580 once invoked, about $0.0004 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 2026-08-31.