{
  "schemaVersion": "1",
  "revision": "22ce5d34dbcb5a78",
  "id": "factory-tools-markdown-agent-flows",
  "slug": "tools-markdown-agent-flows",
  "title": "Markdown agent flows (mdflow)",
  "summary": "Tool roles, alternatives, selection tradeoffs, and compatibility caveats.",
  "category": "Tools",
  "tags": [
    "tools",
    "markdown-agent-flows"
  ],
  "sources": [
    {
      "label": "Tool comparison reference",
      "url": "https://dewy-sleet-n5zs.here.now/#markdown-agent-flows"
    }
  ],
  "sourceUnits": [
    "resources/index.html#markdown-agent-flows"
  ],
  "collection": "factory",
  "categoryId": "tools",
  "wordCount": 327,
  "url": "/topics/factory-tools-markdown-agent-flows/",
  "markdownUrl": "/markdown/factory-tools-markdown-agent-flows.md?raw=1&v=22ce5d34dbcb5a78",
  "jsonUrl": "/api/v1/documents/factory-tools-markdown-agent-flows.json",
  "headings": [
    {
      "id": "markdown-agent-flows-mdflow",
      "text": "Markdown agent flows (mdflow)",
      "level": 2
    },
    {
      "id": "pick-this-if",
      "text": "Pick this if…",
      "level": 3
    }
  ],
  "markdown": "# Markdown agent flows (mdflow)\n\nTool roles, alternatives, selection tradeoffs, and compatibility caveats.\n\n## Markdown agent flows (mdflow)\n\n**John uses:** [mdflow](https://github.com/johnlindquist/mdflow) (`md`, 597, MIT) — executable markdown prompts run against Claude, Codex, Gemini, or Copilot. The differentiators, per section 05: prompt-build-time command inlining (`` !`git status` ``), frontmatter `_inputs`, **isolation from all ambient config/hooks/CLAUDE.md**, and eval-gated evolution (`md feedback` → `md eval` → `md evolve`, proposal-first).\n\n| Alternative | What it is | How it differs | License |\n|----|----|----|----|\n| [Claude Code slash commands & skills (built-in)](https://docs.claude.com/en/docs/claude-code) | Markdown files in .claude/commands and .claude/skills that become reusable parameterized agent behaviors | Ships with the agent — but tied to Claude Code and inherits ambient config; mdflow's isolation and multi-engine targeting are the delta | product docs |\n| [dotprompt](https://github.com/google/dotprompt) | Google's executable GenAI prompt template format (.prompt files: frontmatter + template) | A file-format/spec with runtimes, aimed at app code rather than launching coding agents | Apache-2.0 |\n| [BAML](https://github.com/BoundaryML/baml) | A programming language for agents/prompts with typed inputs/outputs and tests | Full typed DSL + toolchain where mdflow stays plain markdown; heavier but testable | Apache-2.0 |\n| [fabric patterns](https://github.com/danielmiessler/Fabric) | Markdown prompt 'patterns' executed via the fabric CLI against any model | Same 'prompt as a file you run' idea, without engine flags, context inlining, or eval-gated evolution | MIT |\n| [llm templates](https://github.com/simonw/llm) | YAML templates with params for the llm CLI | Lightweight parameterized prompts; no agent-loop execution or tool use | Apache-2.0 |\n\n### Pick this if…\n\n- **Claude Code commands/skills** — you're all-in on one agent; you give up mdflow's isolation and multi-engine targeting.\n- **fabric** — you want \"prompt as a runnable file\" without engine flags or context inlining.\n- **llm templates** — lightweight parameterized prompts, no agent loop.\n- **BAML** — you want types and tests around prompts and will trade markdown simplicity for it.\n- **dotprompt** — you're standardizing prompt files inside application code, not agent launches."
}
