spec-init

A command that starts a new project specification from a detailed description and requirements. It creates a named folder with project metadata and an initial requirements document.

In plain words
What is it for?
Starting feature specifications, recording the project description, and preparing files for later design and task planning.
Why use it?
It gives a new feature a consistent starting structure and checks that its name does not conflict with an existing specification.

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/kbwo/ccmanager/spec-init
Clone the repo
git clone --depth 1 https://github.com/kbwo/ccmanager

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 616 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 $0.00010 $0.00616
Opus 5 $0.00005 $0.00308
Sonnet 5 $0.00002 $0.00123
Haiku 4.5 $0.00001 $0.00062

Measured yesterday against content hash f520df2500df, 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 yesterday.

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 · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Initialization

Initialize a new specification based on the provided project description:

Project Description: $ARGUMENTS

Task: Initialize Specification Structure

SCOPE: This command initializes the directory structure and metadata based on the detailed project description provided.

1. Generate Feature Name

Create a concise, descriptive feature name from the project description ($ARGUMENTS). Check existing .kiro/specs/ directory to ensure the generated feature name is unique. If a conflict exists, append a number suffix (e.g., feature-name-2).

2. Create Spec Directory

Create .kiro/specs/[generated-feature-name]/ directory with:

  • spec.json - Metadata and approval tracking
  • requirements.md - Lightweight template with project description

Note: design.md and tasks.md will be created by their respective commands during the development process.

3. Initialize spec.json Metadata

Create initial metadata with approval tracking:

{
  "feature_name": "[generated-feature-name]",
  "created_at": "current_timestamp",
  "updated_at": "current_timestamp",
  "language": "en",
  "phase": "initialized",
  "approvals": {
    "requirements": {
      "generated": false,
      "approved": false
    },
    "design": {
      "generated": false,
      "approved": false
    },
    "tasks": {
      "generated": false,
      "approved": false
    }
  },
  "ready_for_implementation": false
}

4. Create Requirements Template

Create requirements.md with project description:

# Requirements Document

## Project Description (Input)
$ARGUMENTS

## Requirements
<!-- Will be generated in /kiro:spec-requirements phase -->

5. Update CLAUDE.md Reference

Add the new spec to the active specifications list with the generated feature name and a brief description.

Next Steps After Initialization

Follow the strict spec-driven development workflow:

  1. /kiro:spec-requirements <feature-name> - Create and generate requirements.md
  2. /kiro:spec-design <feature-name> - Create and generate design.md (requires approved requirements)
  3. /kiro:spec-tasks <feature-name> - Create and generate tasks.md (requires approved design)

Read the full file on GitHub · 86 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. yesterday First seen · 86 lines · 10 tokens per session scan A f520df2500df

Subscribe to this mod's changes

spec-init is a command published in the GitHub repository kbwo/ccmanager (1,229 stars, last pushed 2d ago), licensed MIT. It adds 10 tokens to every session and 616 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 2026-08-30.