AgentUp CLAUDE.md

AgentUp CLAUDE.md is an instructions file for coding agents from nolabs-ai/AgentUp. It costs 3,948 tokens per session, scanned A, original, Apache-2.0.

Project instructions for AgentUp, a Python framework for building AI agents. They describe the project structure, technologies, setup, and essential development commands.

In plain words
What is it for?
Use them when developing, testing, configuring, or troubleshooting AgentUp and its YAML-based agents, security controls, plugins, and supported AI providers.
Why use it?
They give a coding agent the context needed to work consistently in the repository instead of making assumptions about how it is organized or run.

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/nolabs-ai/agentup/claude-md
Clone the repo
git clone --depth 1 https://github.com/nolabs-ai/AgentUp

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 AgentUp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nolabs-ai/agentup/claude-md.svg)](https://agentmods.dev/instructions/nolabs-ai/agentup/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nolabs-ai/agentup/claude-md"><img src="https://agentmods.dev/badge/instructions/nolabs-ai/agentup/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,948 This file is loaded in full into every session.
When invoked 3,948 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.03948 $0.03948
Opus 5 $0.01974 $0.01974
Sonnet 5 $0.00790 $0.00790
Haiku 4.5 $0.00395 $0.00395

Measured 4d ago against content hash f0b46b81fe08, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AgentUp CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST http://localhost:8000/ \
CLAUDE.md · 432 lines

How it starts

The opening of the file, as written. The whole thing — 432 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

AgentUp is a Python framework for creating AI agents with production-ready features including security, scalability, and extensibility. It uses a configuration-driven architecture where agent behaviors, data sources, and workflows are defined through YAML configuration rather than code.

Key Features:

  • Configuration-over-code approach with YAML-driven agent definitions
  • Security-first design with scope-based access control and comprehensive audit logging
  • Plugin ecosystem with community registry and automatic security scanning
  • Multi-provider AI support (OpenAI, Anthropic, Ollama)
  • MCP (Model Context Protocol) and A2A (Agent-to-Agent) protocol compliance
  • Real-time operations with streaming, async processing, and push notifications

Technology Stack

  • Python: >=3.11 required
  • Pydantic: v2 for data validation and settings management
  • Web Framework: FastAPI with Uvicorn ASGI server
  • Package Manager: UV (preferred) for dependency management
  • Plugin System: Pluggy-based architecture with middleware inheritance
  • Authentication: OAuth2, JWT, API key support via Authlib
  • Logging: Structlog with correlation IDs for distributed tracing
  • Testing: Pytest with async support and comprehensive markers
  • Code Quality: Ruff (linting/formatting), MyPy (type checking), Bandit (security)

Essential Development Commands

Environment Setup

uv sync --all-extras --dev    # Install all dependencies including dev tools
uv pip install -e .           # Install package in editable mode

Testing

# Unit tests only (fast)
uv run pytest tests/test_*.py tests/test_core/ tests/test_cli/ -v -m "not integration and not e2e and not performance"

# Integration tests
chmod +x tests/integration/int.sh && ./tests/integration/int.sh

# All tests with coverage
uv run pytest tests/ --cov=src --cov-report=html --cov-report=term-missing

# Watch mode for development
uv run pytest-watch --runner "uv run pytest tests/test_*.py tests/test_core/ tests/test_cli/ -m 'not integration and not e2e and not performance'"

Read the full file on GitHub · 432 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 · 432 lines · 3,948 tokens per session scan A f0b46b81fe08

Subscribe to this mod's changes

AgentUp CLAUDE.md is an instructions file published in the GitHub repository nolabs-ai/AgentUp (126 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3,948 tokens to every session, about $0.0197 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.