What is kiro:spec-tasks?

A command that turns an approved feature specification into a detailed list of implementation tasks. A specification describes what a feature should do and how it should be built.

It creates coding tasks from files in a Kiro specification folder after confirming both review approvals.

It prevents task planning from starting before the requirements and design have been reviewed and approved.

How reinhardhq/claude-code-spec-boilerplate configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to reinhardhq/claude-code-spec-boilerplate. 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/reinhardhq/claude-code-spec-boilerplate/main/.claude/commands/kiro:spec-tasks.md

Clone the repo

git clone --depth 1 https://github.com/reinhardhq/claude-code-spec-boilerplate

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/reinhardhq/claude-code-spec-boilerplate/kiro-spec-tasks/github.svg)](https://agentmods.dev/commands/reinhardhq/claude-code-spec-boilerplate/kiro-spec-tasks)

Your own site

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

Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,763 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	$0.00006	$0.02763
Opus 5	$0.00003	$0.01381
Sonnet 5	$0.00001	$0.00553
Haiku 4.5	$0.00001	$0.00276

Measured 10d ago against content hash 8b51a45f873b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

kiro:spec-tasks 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 10d 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-tasks.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Tasks

Generate detailed implementation tasks for feature: $ARGUMENTS

Interactive Approval: Requirements & Design Review

CRITICAL: Tasks can only be generated after both requirements and design are reviewed and approved.

Interactive Review Process

Requirements document: @.kiro/specs/$ARGUMENTS/requirements.md
Design document: @.kiro/specs/$ARGUMENTS/design.md
Spec metadata: @.kiro/specs/$ARGUMENTS/spec.json

Interactive Approval Process:

Check if documents exist - Verify that requirements.md and design.md have been generated
Prompt for requirements review - Ask user: "requirements.mdをレビューしましたか？ [y/N]"
Prompt for design review - Ask user: "design.mdをレビューしましたか？ [y/N]"
If both 'y' (yes): Automatically update spec.json to approve both phases and proceed with tasks generation
If any 'N' (no): Stop execution and instruct user to review respective documents first

Auto-approval update in spec.json when user confirms both reviews:

{
  "approvals": {
    "requirements": {
      "generated": true,
      "approved": true  // ← Automatically set to true when user confirms
    },
    "design": {
      "generated": true,
      "approved": true  // ← Automatically set to true when user confirms
    }
  },
  "phase": "design-approved"
}

User Interaction Example:

📋 Requirements and Design review required before generating tasks.
📄 Please review: .kiro/specs/feature-name/requirements.md
❓ requirements.mdをレビューしましたか？ [y/N]: y
📄 Please review: .kiro/specs/feature-name/design.md
❓ design.mdをレビューしましたか？ [y/N]: y
✅ Requirements and Design approved automatically. Proceeding with tasks generation...

Context Analysis

Complete Spec Context (APPROVED)

Requirements: @.kiro/specs/$ARGUMENTS/requirements.md
Design: @.kiro/specs/$ARGUMENTS/design.md
Current tasks: @.kiro/specs/$ARGUMENTS/tasks.md
Spec metadata: @.kiro/specs/$ARGUMENTS/spec.json

Steering Context

Architecture patterns: @.kiro/steering/structure.md
Development practices: @.kiro/steering/tech.md
Product constraints: @.kiro/steering/product.md

Read the full file on GitHub · 296 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.

10d ago First seen · 296 lines · 6 tokens per session scan A 8b51a45f873b

Subscribe to this mod's changes

kiro:spec-tasks is a command published in the GitHub repository reinhardhq/claude-code-spec-boilerplate (2 stars, last pushed 1y ago), licensed MIT. It adds 6 tokens to every session and 2,763 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.

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

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Implementation Tasks

Interactive Approval: Requirements & Design Review

Interactive Review Process

Context Analysis

Complete Spec Context (APPROVED)

Steering Context

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement