agentflow-cli CLAUDE.md

A guide for the Agentflow API server and command-line tool. It explains the package layout, commands, configuration file, and how to turn an Agentflow graph into a FastAPI web service.

In plain words
What is it for?
Use it when scaffolding, running, building, testing, or evaluating an Agentflow service, or when checking its commands and agentflow.json configuration.
Why use it?
It gives developers one reference for understanding and working with this package. It also separates the API and CLI package from the core framework and other parts of the monorepo, a repository containing multiple related projects.

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/10xhub/agentflow-cli/claude-md
Clone the repo
git clone --depth 1 https://github.com/10xHub/agentflow-cli
Per session 3,664 This file is loaded in full into every session.
When invoked 3,664 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 $0.03664 $0.03664
Opus 5 $0.01832 $0.01832
Sonnet 5 $0.00733 $0.00733
Haiku 4.5 $0.00366 $0.00366

Measured 2d ago against content hash e1b68cb29f51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentflow-cli 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 · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentflow-api (API server + CLI) — Engineering Guide

This file documents the API server and CLI package only (10xscale-agentflow-cli). For the core framework see agentflow/CLAUDE.md; for the TS client, docs, or playground see their folders; for the monorepo overview see the workspace-root CLAUDE.md.

  • Package name (PyPI): 10xscale-agentflow-cli

  • Version: 0.5.0 (pyproject.toml). CLI_VERSION and agentflow_cli.__version__ are single-sourced from the installed distribution metadata (falling back to pyproject.toml only for a non-installed source checkout), so agentflow version reports 0.5.0 consistently.

  • Requires: Python >= 3.12 · Status: 4 - Beta

  • Console entry point: agentflow = agentflow_cli.cli.main:main

  • Depends on the core framework: 10xscale-agentflow>=0.7.0.

  • Depends on the core framework: 10xscale-agentflow>=0.9.0 (0.9.0 is the first release that ships agentflow.core.authz, which the RBAC/scope code imports).

What this package is

It turns an Agentflow CompiledGraph into a production FastAPI service, plus a Typer CLI to scaffold, run, build, test, and evaluate that service. You write a graph, point agentflow.json at it, and agentflow api serves it over REST + WebSocket with auth, rate limiting, media handling, checkpointer/thread management, and a memory store API.

Package layout

Importable package: agentflow_cli/. Two halves:

Path What lives there
agentflow_cli/cli/ The Typer CLI. main.py (command definitions), commands/ (one class per command: api, build, eval, init, skills, test, version), core/ (config, output, validation), constants.py, templates/ (project scaffolds: dev/ minimal, prod/ full)
agentflow_cli/src/app/ The FastAPI app. main.py + loader.py (build app from agentflow.json), routers/ (graph, checkpointer, store, media, ping), core/auth/, core/config/, core/middleware/ (rate_limit, security_headers, request_limits), tasks/, utils/, worker.py

Read the full file on GitHub · 185 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 · 185 lines · 3,664 tokens per session scan A e1b68cb29f51

Subscribe to this mod's changes

agentflow-cli CLAUDE.md is an instructions file published in the GitHub repository 10xHub/agentflow-cli (5 stars, last pushed 15d ago), licensed MIT. It adds 3,664 tokens to every session, about $0.0183 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 2026-08-31.

Related

Other instructions, from other repositories