spec-init

A command that creates a starting folder for a new feature specification and writes initial requirements. A feature specification is a written description of what a software change should do and who it is for.

In plain words
What is it for?
Use it to start a feature spec under .kiro/specs, read optional product context, ask the initial planning questions, and generate requirements-init.md.
Why use it?
It gives feature planning a consistent place and structure, while prompting for the purpose, users, problem, and constraints. It also checks that work happens in an isolated Git worktree, a separate working copy of a repository.

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/kaze-jp/kusa/spec-init
Clone the repo
git clone --depth 1 https://github.com/kaze-jp/kusa

Made for: Claude Code.

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 572 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 $0.00000 $0.00572
Opus 5 $0.00000 $0.00286
Sonnet 5 $0.00000 $0.00114
Haiku 4.5 $0.00000 $0.00057

Measured 2d ago against content hash f1f880a3d984, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-init 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/kiro/spec-init.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Initialize Feature Spec

Initialize a new feature specification directory and generate initial requirements.

Usage

/kiro:spec-init <feature-name>

Instructions

  1. Worktree guard — Before anything else, check if you are working in a git worktree (not on the main/master branch). If you are on the main branch, stop and create a worktree first using the superpowers:using-git-worktrees skill or git worktree add. Do NOT proceed with spec initialization until you are in an isolated worktree.

  2. Read product context from .ao/steering/product.md if it exists. Use this to understand the product vision, target users, and strategic goals.

  3. Create the spec directory at .kiro/specs/$FEATURE_NAME/.

  4. Gather feature information by asking the user:

    • What is the feature's purpose?
    • Who are the target users?
    • What problem does it solve?
    • Are there any known constraints?
  5. Generate requirements-init.md in the spec directory with the following structure:

# Feature: <feature-name>

## Overview
<Brief description of the feature and its purpose>

## Product Context
<Relevant context from product.md>

## Initial Requirements

### Functional Requirements
<List requirements using EARS format>

### Non-Functional Requirements
<Performance, security, accessibility requirements using EARS format>

### Constraints
<Known constraints and limitations>

### Assumptions
<Assumptions made during requirements gathering>

### Open Questions
<Questions that need answers before proceeding>
  1. Apply EARS format for all requirements:

    • Ubiquitous: "The shall "
    • Event-driven: "When , the shall "
    • State-driven: "While , the shall "
    • Optional: "Where , the shall "
    • Unwanted: "If , the shall "
  2. Confirm with the user that the initial requirements capture their intent before finalizing.

Read the full file on GitHub · 74 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 · 74 lines · 0 tokens per session scan A f1f880a3d984

Subscribe to this mod's changes

spec-init is a command published in the GitHub repository kaze-jp/kusa (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 572 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 2026-08-31.