/next-steps

allowed-tools: Task, TodoRead, Read, Write, Bash(git:*), Bash(fd:*), Bash(rg:*), Bash(eza:*), Bash(bat:*), Bash(jq:*), Bash(gdate:*), Bash(gh:*)
name: "Next Steps"
description: "Intelligent project state analyzer with priority-based task recommendations and sub-agent coordination"
author: "wcygan"
tags: ["workflow","view"]
version: "1.0.0"
created_at: "2025-07-14T00:00:00Z"
updated_at: "2025-07-14T00:00:00Z"

Context

• Session ID: !`gdate +%s%N 2>/dev/null || date +%s%N 2>/dev/null || echo "$(date +%s)$(jot -r 1 100000 999999 2>/dev/null || shuf -i 100000-999999 -n 1 2>/dev/null || echo $RANDOM$RANDOM)"`
• Current directory: !`pwd`
• Git status: !`git status --porcelain 2>/dev/null | head -10 || echo "Not a git repository"`
• Current branch: !`git branch --show-current 2>/dev/null || echo "No git repository"`
• Recent commits: !`git log --oneline -5 2>/dev/null || echo "No git history"`
• Project type: !`fd "(package\.json|Cargo\.toml|go\.mod|deno\.json|pom\.xml|build\.gradle)" . -d 2 | head -3 || echo "No build files detected"`
• Current todos: !`jq -r '.todos[] | select(.status != "completed") | "- [" + .status + "] " + .content' ~/.claude/session-todos.json 2>/dev/null | head -5 || echo "No active todos"`
• Task system status: !`cat /tasks/status.json 2>/dev/null | jq -r '"Total: " + (.total | tostring) + ", Active: " + (.active | tostring) + ", Blocked: " + (.blocked | tostring)' || echo "No task system found"`
• Analysis target: $ARGUMENTS

Your Task

STEP 1: Initialize next-steps analysis session with comprehensive state assessment

• CREATE session state file: `/tmp/next-steps-session-$SESSION_ID.json`
• ANALYZE current project context from Context section
• DETERMINE analysis scope based on $ARGUMENTS (general analysis vs. specific focus area)
• ASSESS project complexity and coordination requirements

# Initialize next-steps analysis session
echo '{
  "sessionId": "'$SESSION_ID'",
  "analysisTarget": "'$ARGUMENTS'",
  "projectType": "auto-detect",
  "analysisScope": "comprehensive",
  "priorityFramework": "impact-effort-matrix",
  "recommendations": []
}' > /tmp/next-steps-session-$SESSION_ID.json

STEP 2: Multi-dimensional project state analysis with parallel sub-agent coordination

TRY:

IF project_complexity == "large" OR analysis_scope == "comprehensive":

LAUNCH parallel sub-agents for thorough project state analysis:

• **Agent 1: Git & Version Control Analysis**: Analyze repository state and development flow
• Focus: Branch status, recent commits, merge conflicts, pending PRs, release cycles
• Tools: git commands, gh CLI for GitHub integration, branch analysis
• Output: Development flow assessment and version control recommendations

• **Agent 2: Task & TODO Analysis**: Examine existing work tracking and outstanding items
• Focus: TodoRead analysis, task system status, blocked items, dependency chains
• Tools: TodoRead, task system analysis, priority assessment
• Output: Work queue analysis and priority recommendations

• **Agent 3: Code Quality & Technical Debt**: Assess codebase health and improvement opportunities
• Focus: TODO/FIXME comments, test coverage gaps, refactoring needs, security issues
• Tools: rg for pattern searches, static analysis, coverage reports
• Output: Technical debt assessment and quality improvement roadmap

• **Agent 4: Dependencies & Infrastructure**: Analyze external dependencies and system health
• Focus: Dependency updates, security vulnerabilities, build system health, CI/CD status
• Tools: Package manager analysis, security scanning, build system checks
• Output: Infrastructure and dependency management recommendations

• **Agent 5: Documentation & Knowledge Gaps**: Identify documentation needs and knowledge management
• Focus: Missing documentation, outdated guides, API documentation, onboarding materials
• Tools: fd for doc discovery, rg for documentation patterns, gap analysis
• Output: Documentation strategy and knowledge management improvements

ELSE:

EXECUTE focused single-agent analysis for targeted recommendations:

echo "🎯 Executing focused analysis for: $ARGUMENTS"

Analysis Process

STEP 3: Intelligent priority analysis using impact-effort matrix methodology

TRY:

**Multi-Dimensional Priority Assessment:**

# Priority analysis framework
echo "📊 Applying impact-effort matrix to identified tasks..."

CASE priority_category: WHEN "immediate_blockers":

• IDENTIFY issues preventing other work from proceeding
• ASSESS impact on team productivity and project timeline
• PRIORITIZE by severity and dependency cascade effects
• RECOMMEND immediate action items with clear resolution paths

WHEN "high_impact_opportunities":

• EVALUATE core functionality improvements and critical bug fixes
• ANALYZE user experience impact and business value
• CONSIDER technical feasibility and resource requirements
• RECOMMEND strategic initiatives with measurable outcomes

WHEN "quick_wins":

• DISCOVER small tasks with immediate visible value
• FOCUS on low-effort, high-visibility improvements
• IDENTIFY automation opportunities and developer experience enhancements
• RECOMMEND tactical improvements for momentum building

WHEN "technical_debt":

• ASSESS code quality degradation and maintenance burden
• EVALUATE refactoring opportunities and architecture improvements
• CONSIDER long-term maintainability and team velocity impact
• RECOMMEND strategic technical investments

WHEN "knowledge_gaps":

• IDENTIFY missing documentation and knowledge transfer needs
• ASSESS onboarding efficiency and team knowledge distribution
• EVALUATE API documentation and usage guidance completeness
• RECOMMEND knowledge management and documentation strategies

STEP 4: Intelligent recommendation synthesis with actionable task breakdown

**Structured Recommendation Generation:**

# Generate prioritized recommendations
jq --arg timestamp "$(gdate -Iseconds 2>/dev/null || date -Isecond