openscience CLAUDE.md

Repository instructions for OpenScience, an open-source AI research and engineering agent written in Bun and TypeScript. Bun is a JavaScript runtime, while TypeScript adds types to JavaScript.

In plain words
What is it for?
Running the project in development, checking types, running tests, building binaries, and working with its configuration and provider integrations.
Why use it?
They explain where the frontend, backend, tools, configuration, and binaries live. This reduces guesswork when developing, testing, or building the project for different systems.

Instructions file

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/synthetic-sciences/openscience/claude-md
Clone the repo
git clone --depth 1 https://github.com/synthetic-sciences/openscience
Per session 1,432 This file is loaded in full into every session.
When invoked 1,432 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 $0.01432 $0.01432
Opus 5 $0.00716 $0.00716
Sonnet 5 $0.00286 $0.00286
Haiku 4.5 $0.00143 $0.00143

Measured 2d ago against content hash 7f389c736bc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openscience 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 2d 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 · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md: OpenScience

Project Overview

OpenScience (openscience) is an open-source, model-agnostic AI research agent for ML engineering and scientific work. Built with Bun and TypeScript, it ships as native binaries for Linux, macOS, and Windows.

  • npm package: @synsci/openscience
  • Binary name: openscience
  • Config dir: ~/.config/openscience/ (override with OPENSCIENCE_CONFIG_DIR)
  • Data root: ~/.openscience/ by default (relocatable; legacy synsc data imports automatically)
  • Config file: openscience.json
  • Provider ID: synsci (Atlas wire contract, do not rename)

Repository Structure

Single git repo organized by runtime boundary.

frontend/          workspace (browser UI), docs/share site, and shared UI
backend/           CLI/server, skills, sessions, and provider integrations
tooling/           SDK, plugin runtime, repo automation, launcher, utilities, and patches

Development

# Run CLI in dev mode
bun run dev

# Build all platform binaries
cd backend/cli && bun run build

# Typecheck
bun run typecheck

# Run tests
cd backend/cli && bun test

Prompt Architecture (Dual-Layer)

The CLI uses a dual-layer prompt system: provider-level system prompts + agent-level workflow prompts.

User request with agent name (e.g., "research")
  │
  ├─ Layer 1: SYSTEM role ← provider-neutral product contract
  │   src/session/system.ts supplies one contract to every model
  │
  └─ Layer 2: USER role injection ← agent prompt (task-specific)
      src/session/prompt.ts selects by agent name + tier

Session prompts (src/session/prompt/)

File Purpose
core.txt Provider-neutral operating contract
plan.txt Read-only Plan mode contract
build-switch.txt, max-steps.txt Mode transition and step-limit utilities

Read the full file on GitHub · 131 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. 2d ago First seen · 131 lines · 1,432 tokens per session scan A 7f389c736bc2

Subscribe to this mod's changes

openscience CLAUDE.md is an instructions file published in the GitHub repository synthetic-sciences/openscience (3,385 stars, last pushed today), licensed Apache-2.0. It adds 1,432 tokens to every session, about $0.0072 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.