greenfield

greenfield is a command for Claude Code from benshapyro/cadre-devkit-claude. It costs 9 tokens per session (845 once invoked), scanned A, original, MIT.

A command for discovering and specifying a new software project from scratch.

In plain words
What is it for?
Use it to create project documents covering requirements, users, success criteria, technical design, and an implementation roadmap.
Why use it?
It helps define the problem and the smallest useful product before implementation begins.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths.

Part of the cadre-devkit-claude plugin — 10 skills, 10 commands, 7 agents, 3 hooks shipped together

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/benshapyro/cadre-devkit-claude/greenfield
Clone the repo
git clone --depth 1 https://github.com/benshapyro/cadre-devkit-claude

Made for: Claude Code.

Or install cadre-devkit-claude, the plugin that ships this one along with the rest of its 10 skills, 10 commands, 7 agents, 3 hooks.

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.

agentmods badge for greenfield

README.md
[![agentmods](https://agentmods.dev/badge/commands/benshapyro/cadre-devkit-claude/greenfield.svg)](https://agentmods.dev/commands/benshapyro/cadre-devkit-claude/greenfield)
Your own site
<a href="https://agentmods.dev/commands/benshapyro/cadre-devkit-claude/greenfield"><img src="https://agentmods.dev/badge/commands/benshapyro/cadre-devkit-claude/greenfield.svg" alt="Measured on agentmods" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 845 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 5.1 $0.00009 $0.00845
Opus 5 $0.00005 $0.00423
Sonnet 5 $0.00002 $0.00169
Haiku 4.5 $0.00001 $0.00085

Measured 6d ago against content hash e913d9bd95f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

greenfield 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 6d 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.

commands/greenfield.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Greenfield Command

Transform a new idea into actionable specifications through structured discovery.

Before starting: Read .claude/skills/product-discovery/SKILL.md for methodology and templates.

When to Use

  • Starting a new project from scratch
  • Exploring a vague idea that needs definition
  • Defining MVP scope before implementation

Not for: Adding features to existing projects (use /plan instead)

Output

Creates three documents in docs/:

  • docs/SPEC.md - What to build (requirements, users, success criteria)
  • docs/DESIGN.md - How to build it (architecture, technology choices)
  • docs/PLAN.md - Implementation roadmap (phases, tasks, go/no-go)

Discovery Process

Phase 1: Vision (2-3 questions)

Understand the core idea and motivation.

  • What problem are you solving?
  • Who has this problem?
  • What does success look like?

Phase 2: Core Problem (2-3 questions)

Identify the essential problem to solve first.

  • What's the ONE thing that must work?
  • What's the smallest valuable solution?

Phase 3: Users (2-3 questions)

Define specific user types and their needs.

  • Who is the primary user?
  • What triggers their need?

Phase 4: Technical (2-3 questions)

Explore constraints and technology options.

  • What can be simplified for MVP?
  • What existing tools can be leveraged?

Phase 5: Validation (2-3 questions)

Define success metrics and failure conditions.

  • How will you know it's working?
  • What would make you pivot?

Phase 6: Scoping

Define MVP boundaries using effort-based framing:

Scope Definition
Core MVP ONE problem, ONE user type
Expanded MVP Multiple features, single user focus
Full Vision All features, all users

Workflow

1. User provides idea/problem
2. Interactive discovery (phases 1-6)
3. After each phase: Update relevant doc sections
4. Review complete specs with user
5. Finalize and save to docs/
6. Suggest next step: /plan [first feature]

Read the full file on GitHub · 129 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. 6d ago First seen · 129 lines · 9 tokens per session scan A e913d9bd95f0

Subscribe to this mod's changes

greenfield is a command published in the GitHub repository benshapyro/cadre-devkit-claude (9 stars, last pushed 9mo ago), licensed MIT. It adds 9 tokens to every session and 845 once invoked, about $0.0000 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.