Back to list
groeimetai

snow-flow-commands

by groeimetai

🤖 AI-powered ServiceNow development with 400+ MCP tools. Works with Claude, GPT, Gemini, Ollama & 75+ providers. Deploy widgets, manage incidents, automate workflows - all through natural language. Open-source Build Agent alternative.

42🍴 9📅 Jan 23, 2026

SKILL.md


name: snow-flow-commands description: This skill should be used when the user asks about "snow-flow commands", "CLI commands", "how to start", "swarm", "sparc", "orchestrator", "agent spawn", "memory", "task", or needs guidance on Snow-Flow CLI operations. license: Apache-2.0 compatibility: Designed for Snow-Code CLI metadata: author: groeimetai version: "1.0.0" category: platform tools: []

Snow-Flow CLI Commands

Snow-Flow provides a powerful CLI for ServiceNow development orchestration.

Core Commands

Starting Snow-Flow

# Start interactive TUI
snow-flow

# Start with specific model
snow-flow --model claude-sonnet
snow-flow --model claude-opus
snow-flow --model gpt-4

# Resume previous session
snow-flow --resume
snow-flow --continue

System Status

# Check system status
snow-flow status

# Real-time monitoring
snow-flow monitor

# Version info
snow-flow --version

SPARC Modes

SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) modes provide structured development workflows.

Available Modes

ModeCommandPurpose
OrchestratorsparcMulti-agent coordination
Codersparc run coderDirect implementation
Researchersparc run researcherInvestigation and analysis
TDDsparc tddTest-driven development

Usage

# Orchestrator mode (default)
snow-flow sparc "Create incident dashboard widget"

# Specific mode
snow-flow sparc run coder "Implement auto-assignment business rule"
snow-flow sparc run researcher "Analyze current incident workflow"

# Test-driven development
snow-flow sparc tdd "Add SLA breach notification"

Agent Management

Spawning Agents

# Spawn specialized agent
snow-flow agent spawn developer
snow-flow agent spawn researcher
snow-flow agent spawn reviewer

# List active agents
snow-flow agent list

# Agent status
snow-flow agent status <agent-id>

Agent Types

TypePurpose
developerServiceNow artifact creation
researcherInvestigation and analysis
reviewerCode review and validation
testerTesting and QA

Swarm Coordination

Multi-agent swarms for complex tasks.

# Start swarm with objective
snow-flow swarm "Build HR portal with self-service features"

# Swarm options
snow-flow swarm "objective" --strategy parallel
snow-flow swarm "objective" --strategy sequential
snow-flow swarm "objective" --mode development
snow-flow swarm "objective" --monitor

Swarm Strategies

StrategyDescription
parallelAgents work simultaneously
sequentialAgents work in order
adaptiveDynamic coordination

Task Management

# Create task
snow-flow task create "Implement feature X"

# List tasks
snow-flow task list

# Task status
snow-flow task status <task-id>

# Orchestrate complex task
snow-flow task orchestrate "Multi-step implementation"

Memory Operations

Persistent memory across sessions.

# Store data
snow-flow memory store <key> <data>

# Retrieve data
snow-flow memory get <key>

# List all keys
snow-flow memory list

# Search memory
snow-flow memory search <query>

# Clear memory
snow-flow memory clear

Configuration

# Configure ServiceNow instance
snow-flow config instance <url>

# Set credentials
snow-flow config auth

# View configuration
snow-flow config show

# Reset configuration
snow-flow config reset

Authentication

# Authenticate with ServiceNow
snow-flow auth servicenow

# Authenticate with enterprise services
snow-flow auth enterprise

# Check auth status
snow-flow auth status

# Logout
snow-flow auth logout

Environment Variables

VariablePurpose
SNOWCODE_MODELDefault AI model
SNOWCODE_DEBUG_TOKENSEnable token debugging
SNOWCODE_LOG_LEVELLogging verbosity
SERVICENOW_INSTANCEServiceNow instance URL

Common Workflows

Starting Development Session

# 1. Start snow-flow
snow-flow

# 2. In TUI, create Update Set first
# 3. Develop features
# 4. Complete Update Set when done

Debugging Token Usage

# Enable token debugging
SNOWCODE_DEBUG_TOKENS=true snow-flow

# Check debug output
cat .snow-code/token-debug/debug-*.jsonl | jq .

Multi-Agent Development

# Start swarm for complex feature
snow-flow swarm "Build customer portal" --strategy parallel --monitor

# Monitor progress
snow-flow monitor

TUI Shortcuts

Inside the interactive TUI:

KeyAction
Ctrl+CCancel current operation
Ctrl+DExit
TabAutocomplete
Up/DownNavigate history
/helpShow help
/clearClear screen
/debugToggle debug mode

Best Practices

  1. Always start with Update Set - Track all changes
  2. Use SPARC modes - Structured development
  3. Monitor tokens - Watch context usage
  4. Persist memory - Save important data
  5. Use swarms - For complex multi-part tasks

Score

Total Score

75/100

Based on repository quality metrics

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

+10
説明文

100文字以上の説明がある

+10
人気

GitHub Stars 100以上

0/15
最近の活動

1ヶ月以内に更新

+10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

+5

Reviews

💬

Reviews coming soon