DeepScientist AGENTS.md

DeepScientist AGENTS.md is an instructions file for Codex, OpenCode from ResearAI/DeepScientist. It costs 3,805 tokens per session, scanned A, original, Apache-2.0.

A repository guide for DeepScientist, a local research system that stores project state in files and Git repositories.

In plain words
What is it for?
Understanding the architecture, locating the relevant documentation and source code, following the project’s research-workspace rules, and checking changes against tests and current behavior.
Why use it?
It tells coding agents what to read first, what the project is meant to do, and which parts of the system are within scope.

Instructions file for CodexOpenCode

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

Made for: Codex, OpenCode.

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 AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/researai/deepscientist/agents-md.svg)](https://agentmods.dev/instructions/researai/deepscientist/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/researai/deepscientist/agents-md"><img src="https://agentmods.dev/badge/instructions/researai/deepscientist/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,805 This file is loaded in full into every session.
When invoked 3,805 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 $0.03805 $0.03805
Opus 5 $0.01903 $0.01903
Sonnet 5 $0.00761 $0.00761
Haiku 4.5 $0.00380 $0.00380

Measured 4d ago against content hash 3247b279c287, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

DeepScientist AGENTS.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.

AGENTS.md · 484 lines

How it starts

The opening of the file, as written. The whole thing — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeepScientist Repository Guide

This AGENTS.md applies to the entire repository.

It is the repository-level guide for coding agents and maintainers working in this checkout. It should describe the code and docs that actually exist here today.

When code and docs diverge, prefer the current runtime behavior and tests, then update the docs in the same change.

Mission

Build DeepScientist as a small, local-first research operating system that:

  • runs on the user's machine by default
  • installs cleanly through npm
  • keeps the authoritative runtime in Python
  • uses prompt-led and skill-led workflow control
  • stores durable state in files plus Git
  • keeps one quest as one Git repository
  • supports the full research loop inside one quest workspace

The target is a focused core runtime, not a large platform.

Read First

Do not start from memory. Start from the files that actually exist.

Recommended reading order for coding agents:

  1. README.md
  2. docs/en/README.md
  3. docs/en/90_ARCHITECTURE.md
  4. docs/en/91_DEVELOPMENT.md
  5. the smallest subsystem-specific doc set that matches the task
  6. the actual implementation under src/
  7. the relevant tests under tests/

Important current docs by topic:

  • product and docs index:
    • README.md
    • docs/en/README.md
    • docs/zh/README.md
  • maintainer architecture and workflow:
    • docs/en/90_ARCHITECTURE.md
    • docs/en/91_DEVELOPMENT.md
  • user-facing architecture and workflow:
    • docs/en/13_CORE_ARCHITECTURE_GUIDE.md
    • docs/en/14_PROMPT_SKILLS_AND_MCP_GUIDE.md
    • docs/en/06_RUNTIME_AND_CANVAS.md
    • docs/en/07_MEMORY_AND_MCP.md
  • runtime and settings:
    • docs/en/00_QUICK_START.md
    • docs/en/01_SETTINGS_REFERENCE.md
    • docs/en/05_TUI_GUIDE.md
    • docs/en/09_DOCTOR.md
    • docs/en/31_LOCAL_BROWSER_AUTH.md
    • docs/en/20_WORKSPACE_MODES_GUIDE.md
  • runner/provider setup:
    • docs/en/15_CODEX_PROVIDER_SETUP.md
    • docs/en/24_CLAUDE_CODE_PROVIDER_SETUP.md
    • docs/en/25_OPENCODE_PROVIDER_SETUP.md
    • docs/en/27_KIMI_CODE_PROVIDER_SETUP.md
    • docs/en/21_LOCAL_MODEL_BACKENDS_GUIDE.md
  • connectors:
    • docs/en/03_QQ_CONNECTOR_GUIDE.md
    • docs/en/04_LINGZHU_CONNECTOR_GUIDE.md
    • docs/en/10_WEIXIN_CONNECTOR_GUIDE.md
    • docs/en/16_TELEGRAM_CONNECTOR_GUIDE.md
    • docs/en/17_WHATSAPP_CONNECTOR_GUIDE.md
    • docs/en/18_FEISHU_CONNECTOR_GUIDE.md
    • docs/en/19_EXTERNAL_CONTROLLER_GUIDE.md
  • BenchStore:
    • docs/en/22_BENCHSTORE_YAML_REFERENCE.md
    • docs/en/23_BENCHSTORE_GITHUB_RELEASES_SPEC.md

Read the full file on GitHub · 484 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 · 484 lines · 3,805 tokens per session scan A 3247b279c287

Subscribe to this mod's changes

DeepScientist AGENTS.md is an instructions file published in the GitHub repository ResearAI/DeepScientist (3,310 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3,805 tokens to every session, about $0.0190 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

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