What is mdflow CLAUDE.md?

Project instructions for mdflow, a command-line tool that runs AI-agent workflows written in Markdown files. They document its commands, configuration, and ways to inspect or test a workflow.

Use them when developing or using mdflow. They cover running flows, checking project readiness, creating drafts, capturing conversations, explaining configuration, and rendering workflows.

They help an agent understand how the tool is structured and which command to use for each task. They also reduce mistakes when creating flows or checking their resolved settings.

How johnlindquist/mdflow configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to johnlindquist/mdflow. 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/johnlindquist/mdflow/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/johnlindquist/mdflow

Made for: Claude Code, Codex.

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/johnlindquist/mdflow/claude-md/github.svg)](https://agentmods.dev/instructions/johnlindquist/mdflow/claude-md)

Your own site

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

Per session 8,625 This file is loaded in full into every session.

When invoked 8,625 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	$0.08625	$0.08625
Opus 5.5	$0.03450	$0.03450
Sonnet 5.5	$0.01725	$0.01725
Haiku 4.5	$0.00863	$0.00863

Measured 2mo ago against content hash be2f64fd1497, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mdflow 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 2mo 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 · 599 lines

How it starts

The opening of the file, as written. The whole thing — 599 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.

Overview

mdflow (md) is a CLI tool that executes AI agents defined as markdown files. It parses YAML frontmatter for configuration and passes keys directly as CLI flags to the specified command (claude, codex, gemini, copilot, or any other CLI tool).

CLI Subcommands

md <file.md> [flags]     # Run a flow (bare `md` opens the Flow Workbench)
md doctor [--json]       # Inspect project readiness and safe next actions, no execution (free)
md init [--guided] [-e <eng>] [-y] [--agents] [--print-guide]
                         # Scaffold a starter roster (deterministic, zero engine
                         # turns; --guided runs the interactive setup session)
md create [name]         # Create a flow and a fail-closed draft eval suite
md capture               # Print the guide an in-session agent follows to capture
                         # the current conversation as a flow (free; see src/capture.ts)
md explain <flow.md> [--json]  # Show resolved config without executing (free)
md render <flow.md>      # Inspect, write, or open a rendered flow explanation
md hooks add|list|remove <flow.md> [event…]  # Manage the flow's lifecycle hooks file (free)
md eval <flow.md>        # Run the flow's eval suite (costs engine turns; --plan is free)
md eval add|list|remove|coverage  # Scaffold/manage suites, fail-closed verdicts, CI ratchet (free)
md feedback <flow.md> "msg"  # Record durable evolution evidence (free; `md complain` is an alias)
md evolve plan|propose|show|apply <flow.md|run-id>  # Proposal-first evolution (plan is free)
md install <url|gh:...>  # Install a flow into the registry (see src/registry.ts)
md remove <name>         # Remove an installed registry flow
md list                  # List installed registry flows
md roster [sync] [--agents] [--json]  # Inspect flows / sync the managed operator card
md catalog [--json]      # Machine-readable catalog of every discoverable flow
md setup                 # Configure shell (PATH, aliases)
md logs                  # Show flow log directory
md help                  # Show help

Read the full file on GitHub · 599 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.

2mo ago First seen · 599 lines · 8,625 tokens per session scan A be2f64fd1497

Subscribe to this mod's changes

mdflow CLAUDE.md is an instructions file published in the GitHub repository johnlindquist/mdflow (604 stars, last pushed yesterday), licensed MIT. It adds 8,625 tokens to every session, about $0.0345 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.

mdflow CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mdflow CLAUDE.mdjohnlindquist/mdflow	Instructions file	604	yesterday	MIT	A	8,625	Claude Code, Codex
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

mdflow: Instructions file for Claude Code