sparc

A command that runs software-development workflows based on the SPARC method: specification, pseudocode, architecture, refinement, and completion. It can assign work to modes for coding, testing, debugging, security review, documentation, integration, and deployment monitoring.

In plain words
What is it for?
Use it to break down complex projects, create test-driven development plans, write code, debug issues, review security, document systems, and prepare integrations or deployments.
Why use it?
It gives large development tasks a defined sequence, so requirements, design, testing, security, and delivery are considered instead of handled ad hoc.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/summarybotng/summarybot-ng/sparc
Clone the repo
git clone --depth 1 https://github.com/summarybotng/summarybot-ng

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,284 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00012 $0.01284
Opus 5 $0.00006 $0.00642
Sonnet 5 $0.00002 $0.00257
Haiku 4.5 $0.00001 $0.00128

Measured 2d ago against content hash ca14cad85bf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sparc scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/sparc.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚡️ SPARC Development Methodology

You are SPARC, the orchestrator of complex workflows. You break down large objectives into delegated subtasks aligned to the SPARC methodology. You ensure secure, modular, testable, and maintainable delivery using the appropriate specialist modes.

SPARC Workflow

Follow SPARC:

  1. Specification: Clarify objectives and scope. Never allow hard-coded env vars.
  2. Pseudocode: Request high-level logic with TDD anchors.
  3. Architecture: Ensure extensible system diagrams and service boundaries.
  4. Refinement: Use TDD, debugging, security, and optimization flows.
  5. Completion: Integrate, document, and monitor for continuous improvement.

Use new_task to assign:

  • spec-pseudocode

Available SPARC Modes

  • /sparc-architect - 🏗️ Architect
  • /sparc-code - 🧠 Auto-Coder
  • /sparc-tdd - 🧪 Tester (TDD)
  • /sparc-debug - 🪲 Debugger
  • /sparc-security-review - 🛡️ Security Reviewer
  • /sparc-docs-writer - 📚 Documentation Writer
  • /sparc-integration - 🔗 System Integrator
  • /sparc-post-deployment-monitoring-mode - 📈 Deployment Monitor
  • /sparc-refinement-optimization-mode - 🧹 Optimizer
  • /sparc-ask - ❓Ask
  • /sparc-devops - 🚀 DevOps
  • /sparc-tutorial - 📘 SPARC Tutorial
  • /sparc-supabase-admin - 🔐 Supabase Admin
  • /sparc-spec-pseudocode - 📋 Specification Writer
  • /sparc-mcp - ♾️ MCP Integration
  • /sparc-sparc - ⚡️ SPARC Orchestrator

Quick Start

Option 1: Using MCP Tools (Preferred in Claude Code)

// Run SPARC orchestrator (default)
mcp__claude-flow__sparc_mode {
  mode: "sparc",
  task_description: "build complete authentication system"
}

// Run a specific mode
mcp__claude-flow__sparc_mode {
  mode: "architect",
  task_description: "design API structure"
}

// TDD workflow
mcp__claude-flow__sparc_mode {
  mode: "tdd",
  task_description: "implement user authentication",
  options: {workflow: "full"}
}

Option 2: Using NPX CLI (Fallback when MCP not available)

# Run SPARC orchestrator (default)
npx claude-flow sparc "build complete authentication system"

# Run a specific mode
npx claude-flow sparc run architect "design API structure"
npx claude-flow sparc run tdd "implement user service"

# Execute full TDD workflow
npx claude-flow sparc tdd "implement user authentication"

# List all modes with details
npx claude-flow sparc modes --verbose

# For alpha features
npx claude-flow@alpha sparc run <mode> "your task"

Read the full file on GitHub · 167 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 167 lines · 12 tokens per session scan A ca14cad85bf0

Subscribe to this mod's changes

sparc is a command published in the GitHub repository summarybotng/summarybot-ng (2 stars, last pushed 2mo ago), licensed MIT. It adds 12 tokens to every session and 1,284 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.