/build-project Command

Start an interactive project building workflow for any analysis type.

System Prompt

⚠️ EXECUTION DIRECTIVE: When the user invokes this command, you MUST:

1. IMMEDIATELY execute - no questions, no explanations first
2. ALWAYS show full output from script/tool execution
3. ALWAYS provide summary after execution completes

DO NOT:

• Say "I don't need to take action" - you ALWAYS execute when invoked
• Ask for confirmation unless requires_confirmation: true in frontmatter
• Skip execution even if it seems redundant - run it anyway

The user invoking the command IS the confirmation.

---

Usage

# Interactive mode (recommended) - asks what you want to analyze
/build-project

# With pre-selected analysis type
/build-project markdown-quality
/build-project security-audit
/build-project code-quality

# With scope specification
/build-project --scope docs/
/build-project --scope . --type architecture-review

# With specific deliverables
/build-project --deliverables full-infrastructure
/build-project --deliverables report-only

# Project-scoped build (ADR-159)
/build-project --project CUST-avivatec-fpa

Arguments

Argument	Description	Default
$1	Analysis type (optional)	Interactive selection
--scope	Target directory or pattern	Current directory
--type	Analysis type override	Interactive selection
--deliverables	Output type	PROJECT-PLAN + TASKLIST
--dry-run	Preview without creating files	false

Required Tools

Tool	Purpose	Required
Read	Access source files for analysis	Yes
Glob	Find files matching patterns in scope	Yes
Grep	Search for patterns across codebase	Yes
Write	Create PROJECT-PLAN.md and TASKLIST files	Yes
AskUserQuestion	Gather analysis type and scope selections	Yes
Bash	Run analysis tools (lint, security scan)	Optional
TodoWrite	Track analysis progress	Optional

External Requirements:

• Templates directory: CODITECT-CORE-STANDARDS/TEMPLATES/
• Analysis tools vary by type (markdownlint, eslint, security scanners)

Analysis Types

When invoked without arguments, presents interactive choices:

1. markdown-quality - Lint errors, formatting, documentation quality
2. code-quality - Python/JS lint, type coverage, test coverage
3. security-audit - Vulnerability scan, dependency audit, secrets detection
4. documentation-coverage - Missing docs, outdated content, broken links
5. performance-analysis - Bottlenecks, optimization opportunities
6. architecture-review - Patterns, dependencies, technical debt
7. other - Custom analysis type (user specifies)

Deliverable Options

1. project-plan-tasklist - Standard PROJECT-PLAN.md + TASKLIST-WITH-CHECKBOXES.md
2. full-infrastructure - Also creates agents, commands, scripts, skills
3. automation-only - Scripts to fix issues automatically
4. report-only - Analysis report without action plan

Workflow

<default_behavior> When /build-project is invoked:

1. Discovery Phase

   • Present analysis type options using AskUserQuestion
   • Gather scope selection (single folder, full repo, submodules, custom)
   • Collect deliverable requirements
   • ALWAYS include "Other" option for custom specifications

2. Inventory Phase

   • Use codebase-locator to enumerate folders
   • Count files per folder by type
   • Generate inventory table
   • Identify priority targets based on file count

3. Analysis Phase

   • Select appropriate tools based on analysis type
   • Execute analysis across target scope
   • Aggregate results by severity (Critical/High/Medium/Low)
   • Document findings

4. Deliverable Phase

   • Use templates from CODITECT-CORE-STANDARDS/TEMPLATES/
   • Generate PROJECT-PLAN.md with analysis summary
   • Create TASKLIST-WITH-CHECKBOXES.md with actionable items
   • Create additional infrastructure if requested </default_behavior>

Before completing: - [ ] User confirmed analysis type and scope - [ ] Inventory table generated with accurate counts - [ ] Analysis executed for all target files - [ ] Issues categorized by severity - [ ] PROJECT-PLAN.md follows template structure - [ ] TASKLIST-WITH-CHECKBOXES.md has actionable checkboxes - [ ] All deliverables saved to correct location

Examples

Example 1: Interactive Mode

/build-project

Response presents choices:

## What do you want to analyze and build a project for?

1. **Markdown Quality** - Lint errors, formatting, documentation quality
2. **Code Quality** - Python/JS lint, type coverage, test coverage
3. **Security Audit** - Vulnerability scan, dependency audit, secrets detection
4. **Documentation Coverage** - Missing docs, outdated content, broken links
5. **Performance Analysis** - Bottlenecks, optimization opportunities
6. **Architecture Review** - Patterns, dependencies, technical debt
7. **Other** - Describe your analysis type: ___________

Example 2: Markdown Quality Analysis

/build-project markdown-quality --scope docs/

Output:

## Markdown Quality Analysis - docs/

### Inventory
| Folder | Files | Purpose |
|--------|-------|---------|
| docs/01-getting-started/ | 12 | Quick start guides |
| docs/02-architecture/ | 45 | System design |
| ... | ... | ... |

### Analysis Results
Total Errors: 4,138
- MD040: 1,200 (fenced code language)
- MD036: 800 (emphasis as heading)
- MD032: 600 (lists need blank lines)

### Deliverables Created
- MARKDOWN-QUALITY-PROJECT-PLAN.md
- MARKDOWN-QUALITY-TASKLIST-WITH-CHECKBOXES.md

Example 3: Full Infrastructure Build

/build-project security-audit --deliverables full-infrastructure

Creates:

• SECURITY-AUDIT-PROJECT-PLAN.md
• SECURITY-AUDIT-TASKLIST-WITH-CHECKBOXES.md
• agents/security-audit-specialist.md
• commands/run-security-audit.md
• skills/security-audit/SKILL.md
• scripts/security-audit-runner.py

Example 4: Custom Analysis Type

/build-project --type other

Prompts user to describe custom analysis:

## Custom Analysis Type

Please describe what you want to analyze:
- What aspects of the codebase?
- What tools should be used?
- What issues are you looking for?
- What deliverables do you need?

Integration

Primary Skill

# Invokes interactive-project-builder skill
skills/interactive-project-builder/SKILL.md

Orchestrator Agent

Task(subagent_type="project-builder-orchestrator",
     description="Build project plan",
     prompt="Execute /build-project workflow for {analysis_type} in {scope}")

Supporting Scripts

• scripts/interactive-project-builder.py - Main orchestration
• scripts/codebase-inventory.py - Folder/file inventory
• scripts/analysis-runner.py - Analysis tool execution

Related Commands

• /research-codebase - Deep codebase exploration
• /create-plan - Generic plan creation
• /analyze - Code analysis mode

Templates Used

• CODITECT-CORE-STANDARDS/TEMPLATES/PROJECT-PLAN-TEMPLATE.md
• CODITECT-CORE-STANDARDS/TEMPLATES/TASKLIST-WITH-CHECKBOXES-TEMPLATE.md

Error Handling

Error	Recovery
Analysis tool not installed	Suggest installation command or alternative tool
Scope directory not found	Prompt for valid path
No files match pattern	Expand scope or adjust file types
Analysis timeout	Split into smaller batches

Configuration

Environment variables (optional):

CODITECT_ANALYSIS_OUTPUT_DIR="./analysis-output"
CODITECT_TEMPLATE_DIR="./CODITECT-CORE-STANDARDS/TEMPLATES"
CODITECT_DEFAULT_ANALYSIS_TYPE="markdown-quality"

Success Output

When project build completes:

✅ COMMAND COMPLETE: /build-project
Analysis Type: <type>
Scope: <path>
Files Analyzed: N
Issues Found: Critical: X, High: Y, Medium: Z
Deliverables: PROJECT-PLAN.md, TASKLIST-WITH-CHECKBOXES.md

Output Validation

Before completing, verify output contains:

• Analysis type specified (one of: markdown-quality, code-quality, security-audit, etc.)
• Scope path validated and exists
• Inventory table with folder/file counts
• Analysis results with severity breakdown (Critical/High/Medium/Low)
• PROJECT-PLAN.md created with proper structure
• TASKLIST-WITH-CHECKBOXES.md with actionable items
• Success summary with issue counts

Completion Checklist

Before marking complete:

• Analysis type confirmed
• Scope validated
• Inventory generated
• Analysis executed
• Deliverables created

Failure Indicators

This command has FAILED if:

• ❌ Scope directory not found
• ❌ Analysis tool unavailable
• ❌ No deliverables created
• ❌ Missing inventory table

When NOT to Use

Do NOT use when:

• Single file fix (use /analyze)
• No analysis needed (use /create-plan)
• Just exploring (use /research-codebase)

Anti-Patterns (Avoid)

Anti-Pattern	Problem	Solution
Vague scope	Missing files	Be specific with --scope
Skip confirmation	Wrong analysis	Confirm type first
Ignore inventory	Missed targets	Review inventory table

Principles

This command embodies:

• #3 Complete Execution - Full workflow phases
• #6 Clear, Understandable - Structured output
• #9 Based on Facts - Analysis-based planning

Full Standard: CODITECT-STANDARD-AUTOMATION.md