agentmods.dev

AutoResearchWithEyes CLAUDE.md

AutoResearchWithEyes CLAUDE.md is an instructions file for coding agents from llv22/AutoResearchWithEyes. It costs 951 tokens per session, scanned A, original, MIT.

Project instructions for AutoResearchWithEyes, a research workflow for finding ideas, running pilot experiments, reviewing results, and coordinating the work. It defines shared settings and separate executor and reviewer roles.

In plain words
What is it for?
Use it when operating or extending the AutoResearchWithEyes research workflow, including idea discovery, literature review, experiments, and critical review.
Why use it?
It gives contributors a consistent process and keeps idea generation, execution, and review responsibilities distinct.

Instructions file

not rated 5 1mo ago A scan 951 tokens original MIT
View the source file llv22/AutoResearchWithEyes
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.

agentmods
npx agentmods add instructions/llv22/autoresearchwitheyes/claude-md
Clone the repo
git clone --depth 1 https://github.com/llv22/AutoResearchWithEyes

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 AutoResearchWithEyes CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/llv22/autoresearchwitheyes/claude-md.svg)](https://agentmods.dev/instructions/llv22/autoresearchwitheyes/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/llv22/autoresearchwitheyes/claude-md"><img src="https://agentmods.dev/badge/instructions/llv22/autoresearchwitheyes/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 951 This file is loaded in full into every session.
When invoked 951 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00951 $0.00951
Opus 5 $0.00476 $0.00476
Sonnet 5 $0.00190 $0.00190
Haiku 4.5 $0.00095 $0.00095

Measured 4d ago against content hash 909d070f53d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AutoResearchWithEyes CLAUDE.md 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 4d 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.

CLAUDE.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AutoResearchWithEyes: Centralized Constants

All skills, commands, and agents in this plugin reference these shared constants. Override per-invocation by passing inline arguments (e.g., — pilot budget: 4h).

Models (cross-model, no self-play)

Two roles, two different families — Claude executes, GPT reviews. This adversarial split is the framework's core principle; do not collapse both roles onto one family.

  • EXECUTOR_MODEL = claude-fable-5 (Fable 5) — the Claude Code model that drives the pipeline: idea filtering/synthesis, literature review, novelty judgment, and writing. Use it for more solid idea-discovery output. Run the /autor.* commands under this model (/model fable in Claude Code, or spawn via an Agent with model fable). (Verified available as claude-fable-5 on 2026-07-14.)
  • REVIEWER_MODEL = gpt-5.6-sol — external critical reviewer + divergent brainstorm via Codex MCP. Always run at model_reasoning_effort: xhigh. (Verified via codex exec -m gpt-5.6-sol on 2026-07-14; upgraded from gpt-5.5.)

Note: raw idea generation and review go to REVIEWER_MODEL (Codex/GPT); the EXECUTOR (Claude/Fable 5) orchestrates, filters, and writes. Keeping them in separate families is what makes the review adversarial rather than self-review.

Idea Discovery & Pilot Experiments

  • PILOT_MAX_HOURS = 2 — Skip any pilot estimated to take > 2 hours per GPU. Flag as "needs manual pilot".
  • PILOT_TIMEOUT_HOURS = 3 — Hard timeout: kill pilots exceeding 3 hours. Collect partial results if available.
  • MAX_PILOT_IDEAS = 3 — Pilot at most 3 ideas in parallel. Additional ideas are validated on paper only.
  • MAX_TOTAL_GPU_HOURS = 8 — Total GPU budget for all pilots combined.

Review Loop

  • MAX_ROUNDS = 4 — Maximum review-fix-review iterations in the auto-review loop.
  • POSITIVE_THRESHOLD — Score >= 6/10, or verdict contains "accept", "sufficient", "ready for submission".

Workflow Orchestration

Read the full file on GitHub · 67 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. 4d ago First seen · 67 lines · 951 tokens per session scan A 909d070f53d6

Subscribe to this mod's changes

AutoResearchWithEyes CLAUDE.md is an instructions file published in the GitHub repository llv22/AutoResearchWithEyes (5 stars, last pushed 1mo ago), licensed MIT. It adds 951 tokens to every session, about $0.0048 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens