DeepScientist CLAUDE.md

DeepScientist CLAUDE.md is an instructions file for Claude Code from ResearAI/DeepScientist. It costs 2,335 tokens per session, scanned A, original, Apache-2.0.

A repository guide for DeepScientist, a local research workspace that runs long projects through experiments, web and terminal interfaces, and paper outputs.

In plain words
What is it for?
Installing and starting DeepScientist, checking its runners, running tests, building its interfaces, and validating Python and package files.
Why use it?
It gives a coding agent the project’s purpose, setup steps, commands, and development checks in one place.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

About the project

DeepScientist is a local research studio that manages the cycle from baseline experiments through research findings and paper-ready outputs. Researchers use it to organize autonomous scientific investigations, review progress, and take control when needed. The catalogue add-ons provide workflows and agent integrations for running research projects with it.

ResearAI/DeepScientist · 3,315 stars · on GitHub

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/researai/deepscientist/claude-md
Clone the repo
git clone --depth 1 https://github.com/ResearAI/DeepScientist

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 DeepScientist CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/researai/deepscientist/claude-md.svg)](https://agentmods.dev/instructions/researai/deepscientist/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/researai/deepscientist/claude-md"><img src="https://agentmods.dev/badge/instructions/researai/deepscientist/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,335 This file is loaded in full into every session.
When invoked 2,335 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 5.1 $0.02335 $0.02335
Opus 5 $0.01167 $0.01167
Sonnet 5 $0.00467 $0.00467
Haiku 4.5 $0.00233 $0.00233

Measured 6d ago against content hash 85cd2382959c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

DeepScientist 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 6d 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 · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

DeepScientist is a local-first autonomous research studio that manages long-horizon research workflows. It's a Python-based system with a Node.js launcher, web UI, and TUI, designed to keep research projects moving through baselines, experiments, and paper outputs.

Core principle: One quest = one Git repository. All durable state lives in files and Git.

Quick Start Commands

Installation and Setup

# Install from repository
bash install.sh

# Install with LaTeX runtime
bash install.sh --with-tinytex

# Start DeepScientist
ds

# Check system health
ds doctor

# Check specific runner
ds doctor --runner codex
ds doctor --runner claude
ds doctor --runner opencode

Development Commands

# Run tests
pytest

# Build web UI
npm --prefix src/ui install
npm --prefix src/ui run build

# Build TUI
npm --prefix src/tui install
npm --prefix src/tui run build

# Validate Python syntax
python3 -m compileall src/deepscientist

# Validate packaging
npm pack --dry-run --ignore-scripts

Runtime Commands

# Quest management
ds init                    # Create new quest
ds status                  # Show quest status
ds pause                   # Pause quest
ds resume                  # Resume quest

# LaTeX runtime
ds latex status
ds latex install-runtime

# Configuration
ds config                  # Manage configuration

# Memory and baselines
ds memory                  # Memory operations
ds baseline                # Baseline registry operations

Architecture

Launch Chain

  1. User runs ds (npm global bin)
  2. bin/ds.js ensures uv-managed Python runtime exists at ~/DeepScientist/runtime/python-env
  3. Launcher starts Python daemon
  4. Daemon serves web workspace at http://127.0.0.1:20999
  5. Web UI and TUI consume same daemon API

Runtime Home: ~/DeepScientist/

~/DeepScientist/
├── runtime/          # Launcher-managed runtime (uv Python env, tools)
├── config/           # YAML configuration and baseline registry
├── memory/           # Global memory cards
├── quests/           # One quest per Git repository
├── logs/             # Daemon and runtime logs
└── cache/            # Reusable caches (synced skills)

Read the full file on GitHub · 307 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. 6d ago First seen · 307 lines · 2,335 tokens per session scan A 85cd2382959c

Subscribe to this mod's changes

DeepScientist CLAUDE.md is an instructions file published in the GitHub repository ResearAI/DeepScientist (3,315 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 2,335 tokens to every session, about $0.0117 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 2026-08-30.

Related

Other instructions, from other repositories

bio-gene-to-reference-tree copilot-instructions.md

Copilot instructions for Hongda-Zhao/bio-gene-to-reference-tree, a project described as: Auditable agent skill for resolving protein queries, selecting references, and planning reproducible phylogenetic trees.

Hongda-Zhao/bio-gene-to-reference-tree · 105 tokens

braina GEMINI.md

Instructions for brainets/braina, covering project: braina (brain interaction analysis), 1. project context & purpose, 2. commands, verify environment (all core dependencies) and run the verification test suite for frites + hoi.

brainets/braina · 1,269 tokens

research-automation CLAUDE.md

Instructions for lucafusarbassini/research-automation, covering ricet - research automation framework, project overview, claude-flow mcp, workflow habits and file organization.

lucafusarbassini/research-automation · 904 tokens

shannon-prover CLAUDE.md

Claude Code instructions for SkyShannonProver/shannon-prover, covering shannon prover: claude entry point, current boundary, easycrypt environment, eval safety and current documentation.

SkyShannonProver/shannon-prover · 586 tokens

SciCrucible CLAUDE.md

Claude Code instructions for Xinyang-Li666/SciCrucible, covering 科学知识库, 知识库结构, 可用命令, 项目目录 and 工作原则.

Xinyang-Li666/SciCrucible · 1,107 tokens

torchcell CLAUDE.md

Claude Code instructions for Mjvolk3/torchcell, covering vision -- the virtual cell (north star), for local configs, git worktrees, programming guide and provenance & reproducibility.

Mjvolk3/torchcell · 12,957 tokens