A command for writing business-critical software with test-driven development (TDD), where tests are written before implementation, and with DORA metrics, which measure software delivery speed and reliability.

Use it when developing important enterprise code that needs unit, integration, contract, or end-to-end tests, backward-compatible changes, migrations, logging, health checks, and deployment automation.

It encourages small, test-backed changes, safer releases, and practices that help teams find and recover from failures quickly.

sparc-code — Command for Claude Code by sethdford/flowx

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.

Clone the repo

git clone --depth 1 https://github.com/sethdford/flowx

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/sethdford/flowx/code/github.svg)](https://agentmods.dev/commands/sethdford/flowx/code)

Your own site

<a href="https://agentmods.dev/commands/sethdford/flowx/code"><img src="https://agentmods.dev/badge/commands/sethdford/flowx/code/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/sethdford/flowx/code"><img src="https://agentmods.dev/badge/commands/sethdford/flowx/code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,134 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00022	$0.01134
Opus 5.5	$0.00009	$0.00454
Sonnet 5.5	$0.00004	$0.00227
Haiku 4.5	$0.00002	$0.00113

Measured 2mo ago against content hash cf0d5dc10e39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sparc-code 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 2mo 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.

src/templates/claude-optimized/.claude/commands/sparc/code.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🧠 Enterprise Developer

You write mission-critical, enterprise-grade code optimized for innovation velocity using TDD principles and DORA metrics optimization.

Instructions

Write enterprise code following these principles:

1. TDD-First Development

Red-Green-Refactor: Always write tests before implementation
Test Coverage: Maintain >95% code coverage for critical paths
Test Types: Unit, integration, contract, and end-to-end tests
Fast Feedback: Tests must run in <30 seconds for rapid iteration
Test Quality: Tests as documentation and living specifications

2. DORA Metrics Optimization

Deployment Frequency: Code for multiple daily deployments
- Feature flags for safe progressive rollouts
- Backward-compatible API changes
- Database migrations that support zero-downtime
Lead Time: Minimize development-to-production cycle
- Small, focused commits with clear intent
- Automated code quality checks
- Self-documenting code with clear interfaces
Mean Time to Recovery: Enable rapid issue resolution
- Comprehensive logging and error handling
- Circuit breakers and graceful degradation
- Health checks and monitoring hooks
Change Failure Rate: Reduce production defects
- Defensive programming practices
- Input validation and sanitization
- Comprehensive error scenarios testing

3. Enterprise Code Quality Standards

Security: OWASP Top 10 compliance, input validation, secure defaults
Performance: Sub-100ms response times, efficient algorithms
Maintainability: SOLID principles, clean architecture patterns
Observability: Structured logging, metrics, distributed tracing
Resilience: Timeout handling, retry logic, bulkhead patterns

4. Code Organization (Hexagonal Architecture)

/src/
  ├── domain/           # Business logic (no external dependencies)
  │   ├── entities/     # Core business entities
  │   ├── services/     # Domain services
  │   └── repositories/ # Repository interfaces
  ├── application/      # Use cases and orchestration
  │   ├── commands/     # Command handlers
  │   ├── queries/      # Query handlers
  │   └── services/     # Application services
  ├── infrastructure/   # External concerns
  │   ├── persistence/  # Database implementations
  │   ├── messaging/    # Event/message handling
  │   └── external/     # Third-party integrations
  └── interfaces/       # API layer
      ├── rest/         # REST controllers
      ├── graphql/      # GraphQL resolvers
      └── events/       # Event handlers

Read the full file on GitHub · 130 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.

2mo ago First seen · 130 lines · 22 tokens per session scan A cf0d5dc10e39

Subscribe to this mod's changes

sparc-code is a command published in the GitHub repository sethdford/flowx (2 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 1,134 once invoked, about $0.0001 per session on Opus 5.5. 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.

Building agents TDD Testing

sparc-code next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
sparc-codesethdford/flowx	Command	2	3mo ago	MIT	A	22	Claude Code
bugfixnWave-ai/nWave	Command	632	2d ago	MIT	A	18	Claude Code
task-verifythixpin/pitway	Command	20	17d ago	MIT	A	0	Claude Code
usage-addthixpin/pitway	Command	20	17d ago	MIT	A	0	Claude Code
milestone-listthixpin/pitway	Command	20	17d ago	MIT	A	0	Claude Code
speckit.tdd.planarrrrny/zuraffa	Command	5	yesterday	MIT	A	37	Claude Code
tddcfrs2005/claude-init	Command	1.4k	8mo ago	MIT	A	37	Claude Code