Sponsor Suno AI Music arrow_forward
Slash Command

Make Dogfood

Analyze and enhance Makefiles for complete functionality coverage with auto-generation capability

Type
Slash Command
GitHub stars
339
License
MIT
Repo last updated
Sep 24, 2026

What Make Dogfood is

Make Dogfood is a slash command published in the athola/claude-night-market repository on GitHub, which has about 339 stars. The repository describes itself as: “23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.”

A slash command is a reusable prompt saved as a markdown file and run by typing its name after a slash. In Claude Code, custom commands have been merged into skills: a file in .claude/commands/ and a skill folder in .claude/skills/ both create the same kind of command, and existing command files keep working.

Make Dogfood gives you a repeatable way to run the same instructions without retyping them, optionally with arguments.

How to install Make Dogfood

Claude Code

  1. Download make-dogfood.md from the repository.
  2. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md.
  3. Run it by typing / followed by its name.

Claude Cowork

  1. Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it.
  2. In Customize → Skills, click +, then upload the ZIP.
  3. Run it from any task with / and the skill name.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/abstract/commands/make-dogfood.md, shared under the repository's MIT license. Read the full file on GitHub.

Use the makefile-dogfooder script to analyze, test, and enhance Makefiles across the claude-night-market project with thorough safety checks and auto-generation capabilities.

When To Use

Use this command when you need to:

  • Analyzing Makefile completeness
  • Testing existing make targets
  • Generating missing targets
  • Preparing plugins for release
  • Auditing Makefile coverage across plugins
  • Creating Makefiles for plugins without them

When NOT To Use

Avoid this command if:

  • Writing initial Makefiles from scratch (use --generate-makefiles instead)
  • Debugging specific build failures
  • Creating custom build systems

Parameters

  • --mode: Operation mode (default: analyze)
  • analyze: Only analyze and report gaps (SAFE - no changes)
  • generate: Show generated targets without writing files
  • apply: Write targets to Makefiles (use with --dry-run first)
  • --plugin: Restrict to specific plugin (e.g., --plugin sanctum)
  • Recommended: Test on one plugin before applying to all
  • --dry-run: Preview changes without writing files (HIGHLY RECOMMENDED)
  • Always use this before applying changes for real
  • Shows what will be generated/modified
  • --generate-makefiles: Generate Makefiles for plugins that don't have them
  • Follows attune:makefile-generation pattern
  • Auto-detects language (Python/Rust/TypeScript)
  • Creates standard targets for detected language
  • --preflight-check: Run validation checks before processing
  • Validates directories exist
  • Checks write permissions
  • Detects git repository for rollback
  • --verbose: Show detailed progress and error messages
  • --output: Output format (text|json, default: text)

Workflow

1. Discovery Phase

Scan all Makefiles and build an inventory of existing targets:

  • Find all Makefile and .mk files
  • Extract target definitions and metadata
  • Build dependency graphs
  • Identify plugin type (leaf vs aggregator)

2. Analysis Phase

Evaluate Makefiles against best practices:

  • Check for essential targets (help, clean, test, lint)
  • Identify missing convenience targets (demo, quick-run)
  • Detect anti-patterns and inconsistencies
  • Score each Makefile on completeness (0-100)

3. Testing Phase

Safely validate existing targets:

  • Run make -n for dry-run validation
  • Test help targets and documentation coverage
  • Verify target dependencies exist
  • Check for common runtime issues

4. Generation Phase

Create missing targets based on analysis:

  • Generate LIVE demo targets that run actual CLI tools/scripts
  • Add dogfood targets that run plugin tools on the plugin itself
  • Create quick-run targets for common workflows
  • Ensure demos show REAL output, not static echoes
  • Maintain consistency with existing patterns

Generation Checklist:

  • Does demo-* target run an actual script/tool?
  • Does output show real, dynamic data?
  • Would a user learn something by running this?
  • Is the plugin "eating its own dogfood"?

Examples

# SAFE WORKFLOW (Recommended)

# 1. Analyze all plugins to see what's missing
python3 plugins/abstract/scripts/makefile_dogfooder.py --mode analyze

# 2. Generate for a single plugin (see what would be created)
python3 plugins/abstract/scripts/makefile_dogfooder.py --plugin sanctum --mode generate

# 3. Dry-run to preview changes
python3 plugins/abstract/scripts/makefile_dogfooder.py --plugin sanctum --mode apply --dry-run

# 4. Apply for real
python3 plugins/abstract/scripts/makefile_dogfooder.py --plugin sanctum --mode apply

# 5. Generate Makefiles for plugins missing them
python3 plugins/abstract/scripts/makefile_dogfooder.py --generate-makefiles --mode analyze

# 6. Bulk workflow with safety
…

Safety Features

The script includes thorough safety checks:

  1. Preflight Validation (automatic in apply mode)
  • Directory existence checks
  • Write permission verification
  • Git repository detection
  1. Working Directory Validation
  • Automatic normalization
  • Prevents "file not found" errors
  1. Confirmation Prompt
  • Prompts before applying without --dry-run
  • Prevents accidental changes
  1. Duplicate Detection
  • Checks for existing targets
  • Prevents conflicts and warnings

What This Command Does

  1. Creates detailed inventory of all Makefile targets across the project
  2. Identifies gaps in user-facing functionality using pattern matching
  3. Tests safely without modifying files or running risky operations
  4. Generates missing targets with contextually appropriate templates

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Make Dogfood?

Make Dogfood is a slash command for Claude Code and Claude Cowork from the athola/claude-night-market repository on GitHub. Analyze and enhance Makefiles for complete functionality coverage with auto-generation capability

How do I install Make Dogfood in Claude Code?

Download make-dogfood.md from the repository. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md. Run it by typing / followed by its name.

Can I use Make Dogfood in Claude Cowork?

Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it. In Customize → Skills, click +, then upload the ZIP. Run it from any task with / and the skill name.

Is Make Dogfood safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.