What is SFLOW-AIRunner-MCP-PRD CLAUDE.md?

A CLAUDE.md instruction file for SFLOW-AIRunner-MCP-PRD, an MCP server that schedules and runs Claude Code tasks. It documents the server's rules, setup commands, architecture, dashboard, webhooks, and related features.

Installing dependencies, starting the server with standard or web-enabled transport, understanding its scheduling components, and maintaining the documented architecture.

It gives contributors the project context and operating commands needed to work safely on the server. It also records the requirement to keep the instructions current when the architecture changes.

How floriansmeyers/SFLOW-AIRunner-MCP-PRD configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to floriansmeyers/SFLOW-AIRunner-MCP-PRD. 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/floriansmeyers/SFLOW-AIRunner-MCP-PRD/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/floriansmeyers/SFLOW-AIRunner-MCP-PRD

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/floriansmeyers/sflow-airunner-mcp-prd/claude-md/github.svg)](https://agentmods.dev/instructions/floriansmeyers/sflow-airunner-mcp-prd/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/floriansmeyers/sflow-airunner-mcp-prd/claude-md"><img src="https://agentmods.dev/badge/instructions/floriansmeyers/sflow-airunner-mcp-prd/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/floriansmeyers/sflow-airunner-mcp-prd/claude-md"><img src="https://agentmods.dev/badge/instructions/floriansmeyers/sflow-airunner-mcp-prd/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,325 This file is loaded in full into every session.

When invoked 1,325 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	$0.01325	$0.01325
Opus 5	$0.00662	$0.00662
Sonnet 5	$0.00265	$0.00265
Haiku 4.5	$0.00133	$0.00133

Measured 12d ago against content hash e2b69105be94, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

SFLOW-AIRunner-MCP-PRD 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 12d 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 · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 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.

Rules

Always update CLAUDE.md when making changes that affect architecture, conventions, URL resolution logic, helper functions, or any other information documented here. Keep this file in sync with the codebase.

Overview

Single-file MCP server that schedules and executes Claude Code CLI tasks via cron expressions. Built with FastMCP and stores jobs/runs in SQLite. Features a web dashboard, webhook support, dynamic MCP server creation, and token/cost tracking.

Commands

# Install dependencies
pip install -r requirements.txt

# Run server (stdio transport for Claude Desktop)
python server.py

# Run with SSE transport (enables web dashboard + remote access)
MCP_TRANSPORT=sse python server.py
# Dashboard available at http://localhost:8080/

# Run with ngrok for remote access from claude.ai
NGROK_AUTHTOKEN=your_token python server.py
# ngrok tunnel URL will be printed on startup

Architecture

The server runs three concurrent async components in separate threads:

MCP Server - Exposes 25+ tools via FastMCP (jobs, runs, webhooks, credentials, settings)
Scheduler Loop - Checks every 60 seconds for jobs due based on cron expressions
Run Processor Loop - Picks up pending runs and executes them (handles restarts gracefully)

Jobs execute via claude_agent_sdk using the sdk_query() streaming API. Token usage and costs are parsed from the SDK response.

Directory Structure

├── server.py           # Main MCP server
├── jobs.db             # SQLite database
├── fixed-servers/      # Built-in MCP servers (e.g., email)
│   └── email/
│       ├── server.py
│       └── metadata.json
├── dynamic_servers/    # User-created MCP servers via create_mcp_server tool
│   ├── cat-facts/
│   └── r2-images/
└── deploy/             # Deployment configs (systemd, nginx, deploy script)

Database

SQLite at ./jobs.db with tables:

jobs - Scheduled tasks with cron expressions, prompts, timeout settings
runs - Execution history with output, tokens, cost, state (pending/running/finished/error)
webhooks - HTTP endpoints that trigger prompts with payload templating
settings - Configuration for allowed tools, MCP servers, credentials

Read the full file on GitHub · 138 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.

12d ago First seen · 138 lines · 1,325 tokens per session scan A e2b69105be94

Subscribe to this mod's changes

SFLOW-AIRunner-MCP-PRD CLAUDE.md is an instructions file published in the GitHub repository floriansmeyers/SFLOW-AIRunner-MCP-PRD (24 stars, last pushed 7mo ago), licensed MIT. It adds 1,325 tokens to every session, about $0.0066 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.

Building agents

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

SFLOW-AIRunner-MCP-PRD: Instructions file for Claude Code