Skip to main content

Level 2: Rapid Workflows

Complexity: Low-Medium | Artifacts: Memory/Lightweight files | State: Session-scoped

Level 2 workflows provide lightweight planning or single analysis with fast iteration. They're designed for tasks with relatively clear requirements that don't need full session persistence.

Overview

Included Workflows

WorkflowPurposeArtifactsExecution
lite-planClear requirement developmentmemory://plan-> lite-execute
lite-fixBug diagnosis and fix.workflow/.lite-fix/-> lite-execute
multi-cli-planMulti-perspective tasks.workflow/.multi-cli-plan/-> lite-execute

Common Characteristics

PropertyValue
ComplexityLow-Medium
StateSession-scoped / Lightweight persistence
ExecutionUnified via lite-execute
Use CaseRelatively clear requirements

Workflow 1: lite-plan -> lite-execute

In-memory planning + Direct execution

Command

/workflow:lite-plan "Add user authentication API"
/workflow:lite-execute

Flow Diagram

Process Phases

Phase 1: Code Exploration (Optional)

# If -e flag specified
/workflow:lite-plan -e "Add user authentication API"
  • Multi-angle code analysis via cli-explore-agent
  • Identifies patterns, dependencies, integration points

Phase 2: Complexity Assessment

  • Low: Direct planning without agent
  • Medium/High: Use cli-lite-planning-agent

Phase 3: Planning

  • Load plan schema: ~/.claude/workflows/cli-templates/schemas/plan-json-schema.json
  • Generate plan.json following schema

Phase 4: Confirmation & Selection

  • Display plan summary (tasks, complexity, estimated time)
  • Ask user selections:
    • Confirm: Allow / Modify / Cancel
    • Execution: Agent / Codex / Auto
    • Review: Gemini / Agent / Skip

Phase 5: Execute

  • Build executionContext (plan + explorations + clarifications + selections)
  • Execute via /workflow:lite-execute --in-memory

Artifacts

  • In-memory: memory://plan (not persisted)
  • Optional: .workflow/.lite-exploration/ (if code exploration used)

Use Case

Clear single-module features

Example:

/workflow:lite-plan "Add email validation to user registration form"
/workflow:lite-execute

Workflow 2: lite-fix

Intelligent diagnosis + Fix (5 phases)

Command

/workflow:lite-fix "Login timeout after 30 seconds"
/workflow:lite-execute --in-memory --mode bugfix

# Emergency hotfix mode
/workflow:lite-fix --hotfix "Production database connection failing"

Flow Diagram

Process Phases

Phase 1: Bug Analysis & Diagnosis

  • Intelligent severity pre-assessment (Low/Medium/High/Critical)
  • Parallel cli-explore-agent diagnosis (1-4 angles)

Phase 2: Clarification (Optional)

  • Aggregate clarification needs
  • AskUserQuestion for missing info

Phase 3: Fix Planning

  • Low/Medium severity -> Direct Claude planning
  • High/Critical severity -> cli-lite-planning-agent

Phase 4: Confirmation & Selection

  • Display fix-plan summary
  • User confirms execution method

Phase 5: Execute

  • Execute via /workflow:lite-execute --in-memory --mode bugfix

Artifacts

Location: .workflow/.lite-fix/{bug-slug}-{YYYY-MM-DD}/

.workflow/.lite-fix/
└── login-timeout-fix-2025-02-03/
├── diagnosis-root-cause.json
├── diagnosis-impact.json
├── diagnosis-code-flow.json
├── diagnosis-similar.json
├── diagnoses-manifest.json
├── fix-plan.json
└── README.md

Severity Levels

SeverityDescriptionPlanning Method
LowSimple fix, clear root causeDirect Claude (optional rationale)
MediumModerate complexity, some investigationDirect Claude (with rationale)
HighComplex, multiple components affectedcli-lite-planning-agent (full schema)
CriticalProduction incident, urgentcli-lite-planning-agent + hotfix mode

Hotfix Mode

/workflow:lite-fix --hotfix "Production API returning 500 errors"

Characteristics:

  • Skip most diagnosis phases
  • Minimal planning (direct execution)
  • Auto-generate follow-up tasks for complete fix + post-mortem

Use Cases

  • Bug diagnosis
  • Production emergencies
  • Root cause analysis

Workflow 3: multi-cli-plan -> lite-execute

Multi-CLI collaborative analysis + Consensus convergence

Command

/workflow:multi-cli-plan "Compare Redis vs Memcached for caching"
/workflow:lite-execute

Flow Diagram

Process Phases

Phase 1: Context Gathering

  • ACE semantic search
  • Build context package

Phase 2: Multi-CLI Discussion (Iterative)

  • cli-discuss-agent executes Gemini + Codex + Claude
  • Cross-verification, synthesize solutions
  • Loop until convergence or max rounds

Phase 3: Present Options

  • Display solutions with trade-offs

Phase 4: User Decision

  • User selects solution

Phase 5: Plan Generation

  • cli-lite-planning-agent generates plan
  • -> lite-execute

Artifacts

Location: .workflow/.multi-cli-plan/{MCP-task-slug-date}/

.workflow/.multi-cli-plan/
└── redis-vs-memcached-2025-02-03/
├── context-package.json
├── rounds/
│ ├── round-1/
│ │ ├── gemini-analysis.md
│ │ ├── codex-analysis.md
│ │ ├── claude-analysis.md
│ │ └── synthesis.json
│ ├── round-2/
│ └── ...
├── selected-solution.json
├── IMPL_PLAN.md
└── plan.json

vs lite-plan Comparison

Aspectmulti-cli-planlite-plan
ContextACE semantic searchManual file patterns
AnalysisMulti-CLI cross-verificationSingle planning
IterationMultiple rounds until convergenceSingle round
ConfidenceHigh (consensus-driven)Medium (single perspective)
TimeLonger (multi-round)Faster

Use Cases

  • Multi-perspective analysis
  • Technology selection
  • Solution comparison
  • Architecture decisions

Level 2 Comparison Table

Aspectlite-planlite-fixmulti-cli-plan
PurposeClear requirementsBug diagnosisMulti-perspective
PlanningIn-memorySeverity-basedConsensus-driven
Artifactsmemory://plan.lite-fix/.multi-cli-plan/
Code ExplorationOptional (-e flag)Built-in diagnosisACE search
Multi-CLINoNoYes (Gemini/Codex/Claude)
Best ForSingle-module featuresBug fixesTechnology decisions

Execution: lite-execute

All Level 2 workflows execute via lite-execute:

/workflow:lite-execute --in-memory

Execution Flow

Features

  • Parallel execution for independent tasks
  • Sequential phases for dependent tasks
  • Progress tracking via TodoWrite
  • Optional code review