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.
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.
npx agentmods add instructions/researai/deepscientist/claude-mdgit clone --depth 1 https://github.com/ResearAI/DeepScientistWrote 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.
[](https://agentmods.dev/instructions/researai/deepscientist/claude-md)<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>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 | $0.02335 | $0.02335 |
| Opus 5 | $0.01167 | $0.01167 |
| Sonnet 5 | $0.00467 | $0.00467 |
| Haiku 4.5 | $0.00233 | $0.00233 |
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.
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
- User runs
ds(npm global bin) bin/ds.jsensures uv-managed Python runtime exists at~/DeepScientist/runtime/python-env- Launcher starts Python daemon
- Daemon serves web workspace at
http://127.0.0.1:20999 - 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)
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.
- 6d ago First seen · 307 lines · 2,335 tokens per session scan A 85cd2382959c
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.
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.
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.
research-automation CLAUDE.md
Instructions for lucafusarbassini/research-automation, covering ricet - research automation framework, project overview, claude-flow mcp, workflow habits and file organization.
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.
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.
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.