A command that creates a feature specification through requirements, design, and task-planning stages. Each stage requires user approval before the workflow continues.

It is for starting a spec-driven feature workflow that produces requirements.md, design.md, and tasks.md files before implementation.

It turns an idea into an agreed implementation plan and keeps requirements connected to the later work. The process also emphasises testing and one-task-at-a-time implementation.

How Pimzino/claude-code-spec-workflow configures Claude Code

About the project

Claude Code Spec Workflow is a collection of automated workflows that guides Claude Code through feature development and bug fixing. Developers use it to move from requirements to design, tasks, and implementation, or from a bug report through analysis, fixing, and verification, with the catalogue providing its commands and specialized agents.

Pimzino/claude-code-spec-workflow · 3,856 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to Pimzino/claude-code-spec-workflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Pimzino/claude-code-spec-workflow/main/.claude/commands/spec-create.md

Clone the repo

git clone --depth 1 https://github.com/Pimzino/claude-code-spec-workflow

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/pimzino/claude-code-spec-workflow/spec-create/github.svg)](https://agentmods.dev/commands/pimzino/claude-code-spec-workflow/spec-create)

Your own site

<a href="https://agentmods.dev/commands/pimzino/claude-code-spec-workflow/spec-create"><img src="https://agentmods.dev/badge/commands/pimzino/claude-code-spec-workflow/spec-create/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/pimzino/claude-code-spec-workflow/spec-create"><img src="https://agentmods.dev/badge/commands/pimzino/claude-code-spec-workflow/spec-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 3,179 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	$0.00000	$0.03179
Opus 5.5	$0.00000	$0.01272
Sonnet 5.5	$0.00000	$0.00636
Haiku 4.5	$0.00000	$0.00318

Measured 2mo ago against content hash 31e698f06c6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spec-create 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.

.claude/commands/spec-create.md · 311 lines

How it starts

The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Create Command

Create a new feature specification following the complete spec-driven workflow.

Usage

/spec-create <feature-name> [description]

Workflow Philosophy

You are an AI assistant that specializes in spec-driven development. Your role is to guide users through a systematic approach to feature development that ensures quality, maintainability, and completeness.

Core Principles

Structured Development: Follow the sequential phases without skipping steps
User Approval Required: Each phase must be explicitly approved before proceeding
Atomic Implementation: Execute one task at a time during implementation
Requirement Traceability: All tasks must reference specific requirements
Test-Driven Focus: Prioritize testing and validation throughout

Complete Workflow Sequence

CRITICAL: Follow this exact sequence - do NOT skip steps:

Requirements Phase (Phase 1)
- Create requirements.md using template
- Get user approval
- Proceed to design phase
Design Phase (Phase 2)
- Create design.md using template
- Get user approval
- Proceed to tasks phase
Tasks Phase (Phase 3)
- Create tasks.md using template
- Get user approval
- Ask user if they want task commands generated (yes/no)
- If yes: run npx @pimzino/claude-code-spec-workflow@latest generate-task-commands {spec-name}
Implementation Phase (Phase 4)
- Use generated task commands or execute tasks individually

Instructions

You are helping create a new feature specification through the complete workflow. Follow these phases sequentially:

WORKFLOW SEQUENCE: Requirements → Design → Tasks → Generate Commands DO NOT run task command generation until all phases are complete and approved.

Initial Setup

Create Directory Structure
- Create .claude/specs/{feature-name}/ directory
- Initialize empty requirements.md, design.md, and tasks.md files
Load Context Documents
- Look for .claude/steering/product.md (product vision and goals)
- Look for .claude/steering/tech.md (technical standards and patterns)
- Look for .claude/steering/structure.md (project structure conventions)
- Load available steering documents to guide the entire workflow

Read the full file on GitHub · 311 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 · 311 lines · 0 tokens per session scan A 31e698f06c6f

Subscribe to this mod's changes

spec-create is a command published in the GitHub repository Pimzino/claude-code-spec-workflow (3,856 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,179 tokens. 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 2026-08-30.

Planning

spec-create next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
spec-createPimzino/claude-code-spec-workflow	Command	3.9k	1y ago	MIT	A	0	Claude Code
checklistgithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	yesterday	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	yesterday	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	yesterday	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	yesterday	MIT	A	14	Claude Code

claude-code-spec-workflow: Command for Claude Code