What is Agentflow CLAUDE.md?

Engineering instructions for Agentflow, a Python library for building workflows that coordinate multiple AI agents and preserve their state.

Use them when developing or importing the Agentflow core library, especially when working across its larger monorepo, a repository containing several related packages.

They explain the project’s real package layout, public imports, supported Python version, and development rules, reducing errors caused by its repository structure.

How 10xHub/Agentflow configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to 10xHub/Agentflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/10xHub/Agentflow/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/10xHub/Agentflow

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/10xhub/agentflow/claude-md/github.svg)](https://agentmods.dev/instructions/10xhub/agentflow/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/10xhub/agentflow/claude-md"><img src="https://agentmods.dev/badge/instructions/10xhub/agentflow/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/10xhub/agentflow/claude-md"><img src="https://agentmods.dev/badge/instructions/10xhub/agentflow/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,427 This file is loaded in full into every session.

When invoked 3,427 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.03427	$0.03427
Opus 5.5	$0.01371	$0.01371
Sonnet 5.5	$0.00685	$0.00685
Haiku 4.5	$0.00343	$0.00343

Measured 1mo ago against content hash 30b7234d8e4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Agentflow 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 1mo 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 · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentflow (core Python library) — Engineering Guide

This file documents the core Python framework only (10xscale-agentflow, the package that lives in this folder). For the API/CLI, TS client, docs, or playground, see the CLAUDE.md in their respective folders and the workspace-root CLAUDE.md for the monorepo overview.

Package name (PyPI): 10xscale-agentflow
Version: 1.0.0 (single source of truth: pyproject.toml; agentflow.__version__ resolves from installed distribution metadata, so it cannot drift from this file)
Requires: Python >= 3.12
Importable top-level package lives at agentflow/agentflow/ (this folder is the repo root; the importable package is the nested agentflow/ directory).

What this package is

A graph-based orchestration engine for multi-agent LLM systems. It is LLM-agnostic: you bring the provider SDK (OpenAI / Google GenAI), and Agentflow provides the workflow engine, state, persistence, tools, memory, evaluation, and event publishing. Inspired by LangGraph but simpler.

Working principles for this codebase

Read before writing. The public API is large and re-exported through many __init__.py files. Confirm the real export path before referencing a symbol (see Import Map below).
Examples are the source of truth, not the README. examples/ uses current import paths; the README and several docstrings still show pre-refactor paths (see Known Doc Drift).
Surgical edits. This is Development Status :: 5 - Production/Stable. Don't refactor module boundaries or rename exports without checking every __init__.py that re-exports them.
Keep coverage green. pytest enforces --cov-fail-under=80. New code needs tests.
Optional deps are optional. Provider SDKs, MCP, Postgres, Redis, Qdrant, Mem0, Kafka, RabbitMQ, OTEL, a2a are all extras. Guard imports; never make core import a hard optional dep.

Package layout (real, current)

The importable package is agentflow/agentflow/. Top-level subpackages:

Read the full file on GitHub · 213 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.

1mo ago Changed · +13 lines · +282 tokens per session 30b7234d8e4a
2mo ago Changed · +16 lines · +306 tokens per session 671366a06100
2mo ago First seen · 184 lines · 2,839 tokens per session scan A 757991d709c9

Subscribe to this mod's changes

Agentflow CLAUDE.md is an instructions file published in the GitHub repository 10xHub/Agentflow (21 stars, last pushed 1mo ago), licensed MIT. It adds 3,427 tokens to every session, about $0.0137 per session on Opus 5.5. 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.

Building agents Languages Python agent-framework agentic-ai ai-agents ai-agents-framework anthropic google-genai

Agentflow CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Agentflow CLAUDE.md10xHub/Agentflow	Instructions file	21	1mo ago	MIT	A	3,427	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Agentflow: Instructions file for Claude Code