markdown-agent

markdown-agent

review.claude.md                 # Run with Claude
commit.gemini.md "fix auth bug"  # Run with Gemini
git diff | explain.claude.md     # Pipe through any command

Your markdown files are now executable AI agents.

What Is This?

Markdown files become first-class CLI commands. Write a prompt in markdown, run it like a script. The command is inferred from the filename.

# review.claude.md
---
model: opus
---
Review this code for bugs and suggest improvements.

@./src/**/*.ts

review.claude.md                 # Runs: claude --model opus <prompt>
review.claude.md --verbose       # Pass extra flags

How It Works

1. Filename → Command

Name your file task.COMMAND.md and the command is inferred:

task.claude.md    # Runs claude
task.gemini.md    # Runs gemini
task.codex.md     # Runs codex
task.copilot.md   # Runs copilot (print mode by default)

2. Frontmatter → CLI Flags

Every YAML key becomes a CLI flag passed to the command:

---
model: opus              # → --model opus
dangerously-skip-permissions: true  # → --dangerously-skip-permissions
mcp-config: ./mcp.json   # → --mcp-config ./mcp.json
add-dir:                 # → --add-dir ./src --add-dir ./tests
  - ./src
  - ./tests
---

3. Body → Prompt

The markdown body is passed as the final argument to the command.

Unix Philosophy

markdown-agent embraces the Unix philosophy:

• No magic mapping - Frontmatter keys pass directly to the command
• Stdin/stdout - Pipe data in and out
• Composable - Chain agents together
• Transparent - See what runs in logs

# Pipe input
git diff | ma review.claude.md

# Chain agents
ma plan.claude.md | ma implement.codex.md

Installation

npm install -g markdown-agent
# or
bun install && bun link

Quick Start

# Run with filename-inferred command
ma task.claude.md
ma task.gemini.md

# Override command via --command flag
ma task.md --command claude
ma task.md -c gemini

# Pass additional flags to the command
ma task.claude.md --verbose --debug

Note: Both ma and markdown-agent commands are available.

Command Resolution

Commands are resolved in this priority order:

• CLI flag: --command claude or -c claude
• Filename pattern: task.claude.md → claude

If no command can be resolved, you'll get an error with instructions.

Flag Hijacking

Some CLI flags are "hijacked" by markdown-agent—they're consumed and never passed to the underlying command. This allows generic markdown files without command names to be executed.

--command / -c

Override the command for any markdown file:

# Run a generic .md file with any command
ma task.md --command claude
ma task.md -c gemini

# Override the filename-inferred command
ma task.claude.md --command gemini  # Runs gemini, not claude

$varname Fields

Frontmatter fields starting with $ (except $1, $2...) hijack their corresponding CLI flags:

---
$feature_name: Authentication   # Default value
$target_dir: src/features       # Default value
---
Build {{ feature_name }} in {{ target_dir }}.

# Use defaults
ma create.claude.md

# Override with CLI flags (hijacked, not passed to command)
ma create.claude.md --feature_name "Payments" --target_dir "src/billing"

The --feature_name and --target_dir flags are consumed by markdown-agent for template substitution—they won't be passed to the command.

Frontmatter Reference

System Keys (handled by markdown-agent)

Field	Type	Description
args	string[]	Named positional arguments for template variables
env	object	Set process environment variables
env	string[]	Pass as --env flags to command
$1, $2...	string	Map positional args to flags (e.g., $1: prompt)
_interactive / _i	boolean	Enable interactive mode (overrides print-mode defaults)
_subcommand	string/string[]	Prepend subcommand(s) to CLI args

All Other Keys → CLI Flags

Every other frontmatter key is passed directly to the command:

---
model: opus                           # → --model opus
dangerously-skip-permissions: true    # → --dangerously-skip-permissions
mcp-config: ./mcp.json                # → --mcp-config ./mcp.json
p: true                               # → -p (single char = short flag)
---

Value conversion:

• key: "value" → --key value
• key: true → --key
• key: false → (omitted)
• key: [a, b] → --key a --key b

Print vs Interactive Mode

All commands run in print mode by default (non-interactive, exit after completion). Use the .i. filename marker, _interactive frontmatter, or CLI flags to enable interactive mode.

Print Mode (Default)

task.claude.md      # Runs: claude --print "..."
task.copilot.md     # Runs: copilot --silent --prompt "..."
task.codex.md       # Runs: codex exec "..."
task.gemini.md      # Runs: gemini "..." (one-shot)

Interactive Mode

Add .i. before the command name in the filename:

task.i.claude.md    # Runs: claude "..." (interactive session)
task.i.copilot.md   # Runs: copilot --silent --interactive "..."
task.i.codex.md     # Runs: codex "..." (interactive session)
task.i.gemini.md    # Runs: gemini --prompt-interactive "..."

Or use _interactive (or _i) in frontmatter:

---
_interactive: true   # or _interactive: (empty), or _i:
model: opus
---
Review this code with me interactively.

Or use CLI flags:

ma task.claude.md --_interactive  # Enable interactive mode
ma task.claude.md -_i             # Short form

Global Configuration

Set default frontmatter per command in ~/.markdown-agent/config.yaml:

commands:
  claude:
    model: sonnet # Default model for claude
  copilot:
    silent: true  # Always use --silent for copilot

Built-in defaults: All commands default to print mode with appropriate flags per CLI tool.

Examples

Claude with MCP Server

# db.claude.md
---
model: opus
mcp-config: ./postgres-mcp.json
dangerously-skip-permissions: true
---
Analyze the database schema and suggest optimizations.

Gemini YOLO Mode

# refactor.gemini.md
---
model: gemini-3-pro-preview
yolo: true
---
Refactor the authentication module to use async/await.

Codex with Sandbox

# analyze.codex.md
---
model: o3
sandbox: workspace-write
full-auto: true
---
Analyze this codebase and suggest improvements.

Copilot (no frontmatter needed!)

# task.copilot.md
Explain this code.

This runs: copilot --silent --prompt "Explain this code." (print mode)

For interactive mode, use .i. in the filename:

# task.i.copilot.md
Explain this code.

This runs: copilot --silent --interactive "Explain this code."

Template Variables with Args

# create-feature.claude.md
---
args: [feature_name, target_dir]
model: sonnet
---
Create a new feature called "{{ feature_name }}" in {{ target_dir }}.

ma create-feature.claude.md "Auth" "src/features"

Environment Variables

# api-test.claude.md
---
env:
  API_URL: https://api.example.com
  DEBUG: "true"
---
Test the API at !`echo $API_URL`

Imports & Command Inlines

Inline content from other files or command output directly in your prompts.

File Imports

Use @ followed by a path to inline file contents:

---
model: claude
---
Follow these coding standards:
@~/.config/coding-standards.md

Now review this code:
@./src/api.ts

• @~/path - Expands ~ to home directory
• @./path - Relative to current markdown file
• @/path - Absolute path

Imports are recursive—imported files can have their own @ imports.

Glob Imports

Use glob patterns to include multiple files at once:

Review all TypeScript files in src:
@./src/**/*.ts

Glob imports:

• Respect .gitignore automatically
• Include common exclusions (node_modules, .git, etc.)
• Are limited to ~100,000 tokens by default
• Set MA_FORCE_CONTEXT=1 to override the token limit

Files are formatted as XML with path attributes:

<api path="src/api.ts">
...file content...
</api>

<utils path="src/utils.ts">
...file content...
</utils>

Line Range Imports

Extract specific lines from a file:

@./src/api.ts:10-50

This imports only lines 10-50 from the file.

Symbol Extraction

Extract specific TypeScript/JavaScript symbols (interfaces, types, functions, classes, etc.):

@./src/types.ts#UserInterface
@./src/api.ts#fetchUser

Supported symbols:

• interface Name { ... }
• type Name = ...
• function Name(...) { ... }
• class Name { ... }
• const/let/var Name = ...
• enum Name { ... }

Command Inlines

Use !`command` to execute a shell command and inline its output:

Current branch: !`git branch --show-current`
Recent commits:
!`git log --oneline -5`

Based on the above, suggest what to work on next.

URL Imports

Fetch content from URLs (markdown and JSON only):

@https://raw.githubusercontent.com/user/repo/main/README.md

Environment Variables

markdown-agent automatically loads .env files from the markdown file's directory.

Loading Order

Files are loaded in order (later files override earlier):

• .env - Base environment
• .env.local - Local overrides (not committed)
• .env.development / .env.production - Environment-specific
• .env.development.local / .env.production.local - Environment-specific local

Example

my-agents/
├── .env                    # API_KEY=default
├── .env.local              # API_KEY=my-secret (gitignored)
└── review.claude.md

Environment variables are available:

• In command inlines: !`echo $API_KEY`
• In the spawned command's environment

CLI Options

Usage: ma <file.md> [any flags for the command]
       ma <file.md> --command <cmd>
       ma --setup
       ma --logs
       ma --help

Command resolution:
  1. --command flag (e.g., ma task.md --command claude)
  2. Filename pattern (e.g., task.claude.md → claude)

All frontmatter keys are passed as CLI flags to the command.
Global defaults can be set in ~/.markdown-agent/config.yaml

ma-specific flags (consumed, not passed to command):
  --command, -c       Specify command to run
  --dry-run           Preview without executing
  --_interactive, -_i Enable interactive mode

Examples:
  ma task.claude.md -p "print mode"
  ma task.claude.md --model opus --verbose
  ma commit.gemini.md
  ma task.md --command claude
  ma task.md -c gemini
  ma task.claude.md -_i  # Run in interactive mode

Without a file:
  ma --setup    Configure shell to run .md files directly
  ma --logs     Show log directory
  ma --help     Show this help

Environment Variables

Variable	Description
MA_FORCE_CONTEXT	Set to 1 to disable the 100k token limit for glob imports
NODE_ENV	Controls which .env.[NODE_ENV] file is loaded (default: development)

Shell Setup

Make .md files directly executable:

ma --setup   # One-time setup

Then run agents directly:

task.claude.md                   # Just type the filename
task.claude.md --verbose         # With passthrough args

Manual Setup (zsh)

Add to ~/.zshrc:

alias -s md='ma'
export PATH="$HOME/agents:$PATH"  # Your agent library

Building Your Agent Library

Create a directory of agents and add it to PATH:

~/agents/
├── review.claude.md     # Code review
├── commit.gemini.md     # Commit messages
├── explain.claude.md    # Code explainer
├── test.codex.md        # Test generator
└── debug.claude.md      # Debugging helper

export PATH="$HOME/agents:$PATH"

Now use them from anywhere:

review.claude.md                 # Review current directory
commit.gemini.md "add auth"      # Generate commit message
git diff | review.claude.md      # Review staged changes

Notes

• If no frontmatter is present, the file is printed as-is (unless command inferred from filename)
• Template system uses LiquidJS - supports conditionals, loops, and filters
• Logs are always written to ~/.markdown-agent/logs/<agent-name>/ for debugging
• Use --logs to show the log directory
• Stdin is wrapped in <stdin> tags and prepended to the prompt