Sponsor Suno AI Music arrow_forward
Slash Command

Blueprint

Generate an implementation plan with system architecture design and dependency-ordered task breakdown from a specification.

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

What Blueprint is

Blueprint 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.

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

How to install Blueprint

Claude Code

  1. Download blueprint.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/attune/commands/blueprint.md, shared under the repository's MIT license. Read the full file on GitHub.

Transform specifications into executable implementation plans with system architecture, component design, and dependency-ordered task breakdown.

When To Use

Use this command when you need to:

  • Convert specification into implementation plan
  • Design system architecture from requirements
  • Break down work into dependency-ordered tasks
  • Estimate effort and plan sprints
  • Define component interfaces and data flow
  • Create concrete roadmap for execution

When NOT To Use

Avoid this command if:

  • No specification exists yet (use /attune:specify first)
  • Still defining requirements (complete specification phase)
  • Ready to execute existing plan (use /attune:execute instead)
  • Adjusting running project (update plan incrementally)

Usage

# Create plan from specification
/attune:blueprint

# Plan with custom input
/attune:blueprint --input docs/specification.md

# Focus on specific component
/attune:blueprint --component "authentication"

What This Command Does

  1. Loads specification from specify phase
  2. Invokes planning skill with superpowers integration
  3. Designs system architecture (components, interfaces, data flow)
  4. Breaks down into tasks with dependencies and estimates
  5. Produces implementation plan for execution phase

Integration with Superpowers

When superpowers plugin is available:

  • Uses Skill(superpowers:writing-plans) for structured planning
  • Applies dependency analysis
  • Creates checkpoint-based execution flow

Without superpowers:

  • Falls back to attune's native planning skill
  • Provides similar step-by-step approach
  • Documents tasks systematically

Workflow

# 1. Invoke planning skill
Skill(attune:project-planning)

# 2. Design architecture:
#    - System components
#    - Component interfaces
#    - Data flow diagrams
#    - Technology selections

# 3. Break down into tasks:
#    - Development tasks with dependencies
#    - Testing tasks
#    - Deployment tasks
#    - Documentation tasks

# 4. Generate implementation plan
#    - Saved to docs/implementation-plan.md
#    - Includes architecture + task breakdown
…

Workflow Continuation Protocol (MANDATORY)

After planning completes successfully, auto-proceed to the next phase unless --standalone was specified:

  1. Verify artifact: Confirm docs/implementation-plan.md exists and is non-empty
  2. Checkpoint message: Display brief summary to user:
   Implementation plan complete. Saved to docs/implementation-plan.md.
   Proceeding to execution phase...
  1. Auto-invoke next phase:
   Skill(attune:project-execution)

Bypass Conditions (skip auto-continuation if ANY true):

  • --standalone flag was provided
  • docs/implementation-plan.md does not exist or is empty
  • User explicitly requests to stop after planning

Plan Structure

Section 1: Architecture Design

Components:

## System Architecture

### Component Diagram

┌─────────────┐ ┌──────────────┐ ┌─────────────┐ │ Web UI │─────▶│ API Server │─────▶│ Database │ │ (React) │ │ (FastAPI) │ │ (Postgres) │ └─────────────┘ └──────────────┘ └─────────────┘ │ ▼ ┌──────────────┐ │ GitHub API │ └──────────────┘


### Components

#### Component 1: Web UI
**Responsibility**: User interface for debt tracking
**Technology**: React 18 + TypeScript + Vite
**Interfaces**:
- REST API client
- OAuth callback handler
**Data**: Client-side state management (React Context)

#### Component 2: API Server
**Responsibility**: Business logic and GitHub integration
**Technology**: FastAPI + Python 3.10
**Interfaces**:
- REST API endpoints
- GitHub webhook receiver
- Database access layer
…

Section 2: Task Breakdown

Task Format:

### TASK-001: [Task Name]

**Description**: Clear description of what needs to be done

**Type**: Implementation | Testing | Documentation | Deployment
**Priority**: P0 (Critical) | P1 (High) | P2 (Medium) | P3 (Low)
**Estimate**: [Story points or hours]
**Dependencies**: TASK-002, TASK-005
**Assignee**: [Team member or TBD]

**Acceptance Criteria**:
- [ ] Criterion 1
- [ ] Criterion 2

**Technical Notes**:
- Implementation detail 1
- Implementation detail 2
…

Section 3: Development Phases

Phase 1: Foundation (Weeks 1-2)

  • Project initialization
  • Database schema
  • GitHub OAuth setup
  • Basic API scaffolding

Phase 2: Core Features (Weeks 3-6)

  • Issue discovery
  • Prioritization algorithm
  • Dashboard implementation

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 Blueprint?

Blueprint is a slash command for Claude Code and Claude Cowork from the athola/claude-night-market repository on GitHub. Generate an implementation plan with system architecture design and dependency-ordered task breakdown from a specification.

How do I install Blueprint in Claude Code?

Download blueprint.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 Blueprint 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 Blueprint 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.