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/openscientist-io/openscientist/claude-mdgit clone --depth 1 https://github.com/openscientist-io/openscientistWrote 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/openscientist-io/openscientist/claude-md)<a href="https://agentmods.dev/instructions/openscientist-io/openscientist/claude-md"><img src="https://agentmods.dev/badge/instructions/openscientist-io/openscientist/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 | $0.01566 | $0.01566 |
| Opus 5 | $0.00783 | $0.00783 |
| Sonnet 5 | $0.00313 | $0.00313 |
| Haiku 4.5 | $0.00157 | $0.00157 |
Grade A, and why
openscientist 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.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenScientist Development Guide
OpenScientist (Scientific Hypothesis Agent for Novel Discovery) is a web application that runs autonomous AI agents for scientific data analysis and hypothesis testing.
Project Structure
src/openscientist/
├── agent/ # AgentExecutor protocol and ClaudeCodeAgent
├── api/ # FastAPI REST endpoints
├── auth/ # Authentication (OAuth, sessions, middleware)
├── database/ # SQLAlchemy models and migrations
├── job/ # Job lifecycle, scheduling, and types
├── job_container/ # Container-per-job isolation
├── mcp_server/ # MCP server for agent tools
├── orchestrator/ # Discovery orchestration (setup, iteration, report)
├── providers/ # LLM provider abstractions (Anthropic, Vertex, etc.)
├── tools/ # @tool-decorated callables for SDK agent path
├── webapp_components/# NiceGUI pages and components
├── prompts.py # Agent system prompts
├── settings.py # Pydantic settings with TOML support
└── web_app.py # Main application entry point
Development Setup
# Install dependencies
uv sync
# Set up environment variables (see .env.example)
export DATABASE_URL="postgresql+asyncpg://..."
export OPENSCIENTIST_SECRET_KEY="$(openssl rand -hex 32)"
export ANTHROPIC_API_KEY="..." # or other provider credentials
# Run database migrations
uv run alembic upgrade head
# Start development server
uv run python -m openscientist.web_app --reload
Testing
# Run all tests
uv run pytest
# Run with coverage
uv run pytest --cov=openscientist
Testing Conventions
Use real database objects, not mocks. Tests use testcontainers to spin up a real PostgreSQL database. Always create real SQLAlchemy model instances instead of mock classes:
# GOOD: Create real database records
@pytest_asyncio.fixture
async def test_job(db_session: AsyncSession, webapp_user: User) -> Job:
job = Job(
owner_id=webapp_user.id,
title="Test research question",
status="pending",
)
db_session.add(job)
await db_session.commit()
return job
# BAD: Don't create mock classes that bypass the database
class MockJobInfo: # Don't do this
job_id = "fake-id"
status = "pending"
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.
- 4d ago First seen · 199 lines · 1,566 tokens per session scan A 0814967f3125
openscientist CLAUDE.md is an instructions file published in the GitHub repository openscientist-io/openscientist (49 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,566 tokens to every session, about $0.0078 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
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).
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.
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.
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.
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).
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.