A command that breaks a feature specification into four task groups—database, backend, frontend, and integration—and creates self-contained prompts for Claude Code. A feature specification describes what should be built and its requirements.

Use it to create checklists, initial tests, verification commands, and handoff prompts for implementing a feature from an existing specification.

It turns a broad specification into ordered, test-first work that separate coding-agent sessions can carry out with the needed project context.

sdd-tasks — Command for Claude Code by maquina-app

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.

Clone the repo

git clone --depth 1 https://github.com/maquina-app/rails-claude-code

Made for: Claude Code.

Or install spec-driven-development, the plugin that ships this one along with the rest of its 1 skill, 6 commands.

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/maquina-app/rails-claude-code/sdd-tasks.svg)](https://agentmods.dev/commands/maquina-app/rails-claude-code/sdd-tasks)

Your own site

<a href="https://agentmods.dev/commands/maquina-app/rails-claude-code/sdd-tasks"><img src="https://agentmods.dev/badge/commands/maquina-app/rails-claude-code/sdd-tasks.svg" alt="Measured on agentmods" height="20"></a>

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 356 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	$0.00013	$0.00356
Opus 5	$0.00006	$0.00178
Sonnet 5	$0.00003	$0.00071
Haiku 4.5	$0.00001	$0.00036

Measured 7d ago against content hash 94c94e89e94d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sdd-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 7d 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.

spec-driven-development/commands/sdd-tasks.md · 40 lines

What it actually says

Create the task breakdown for the current feature spec using the spec-driven-development skill.

Setup

Read:

sdd/progress.yml to find the current spec folder
sdd/specs/[folder]/spec.md for requirements
sdd/specs/[folder]/references.md for existing code to follow
sdd/specs/[folder]/standards.md for applicable standards

Task Groups

Break the spec into 4 groups following this order: Database → Backend → Frontend → Integration

Each group must have:

A clear goal statement
Specific, actionable tasks with checkboxes
2–5 tests to write first (before implementing)
A verify command: source ~/.zshrc && bin/rails test [path]

Self-Contained Claude Code Prompts

After the task checklist for each group, write a ## PROMPT — Group N section that a Claude Code agent can execute independently with zero additional context. Each prompt must embed:

The task checklist for that group
The full content of standards.md (copy it inline — not a reference)
The relevant sections from references.md
The "done when" verify command

This design means each group's prompt can be handed off to a separate Claude Code session or subagent.

Test counts

2–5 tests per group, 10–20 total
Never more than 8 per group — if needed, split the feature

Write everything to sdd/specs/[folder]/tasks.md. Update sdd/progress.yml when complete.

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.

7d ago First seen · 40 lines · 13 tokens per session scan A 94c94e89e94d

Subscribe to this mod's changes

sdd-tasks is a command published in the GitHub repository maquina-app/rails-claude-code (47 stars, last pushed 21d ago), licensed MIT. It adds 13 tokens to every session and 356 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.

Building agents Planning

sdd-tasks

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Setup

Task Groups

Self-Contained Claude Code Prompts

Test counts

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement