feature-planning

A guided command for planning a new software feature from its description through implementation tasks. It gathers requirements, creates a PRD (product requirements document) and SDD (technical design document), then produces task files.

In plain words
What is it for?
Use it to ask planning questions, generate and review requirements and design documents, and create ordered tasks in TASKS.json and TASKS.md.
Why use it?
It provides a repeatable planning process so important requirements and technical decisions are captured before coding begins.

Command

Part of the shipspec plugin — 6 skills, 5 commands, 6 agents, 1 hook 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/jsegov/shipspec-claude-code-plugin/feature-planning
Clone the repo
git clone --depth 1 https://github.com/jsegov/shipspec-claude-code-plugin

Or install shipspec, the plugin that ships this one along with the rest of its 6 skills, 5 commands, 6 agents, 1 hook.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,805 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 $0.00011 $0.03805
Opus 5 $0.00005 $0.01903
Sonnet 5 $0.00002 $0.00761
Haiku 4.5 $0.00001 $0.00380

Measured 3d ago against content hash 726066fcda35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-planning 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 3d 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/feature-planning.md · 506 lines

How it starts

The opening of the file, as written. The whole thing — 506 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Planning

Guide the user through the complete feature planning workflow from requirements gathering to implementation tasks.

Workflow Overview

This command runs through 7 phases:

  1. Feature Description - Gather or confirm the feature description
  2. Setup - Create planning directory and extract codebase context
  3. Requirements Gathering - Interactive Q&A with prd-gatherer agent
  4. PRD Generation - Generate PRD and pause for user review
  5. Technical Decisions - Interactive Q&A with design-architect agent
  6. SDD Generation - Generate SDD and pause for user review
  7. Task Generation - Automatically generate implementation tasks (TASKS.json + TASKS.md)

Phase 1/7: Feature Description

Goal: Gather a detailed description of the feature to guide all downstream work.

If description provided as argument ($ARGUMENTS is not empty):

Use the provided argument as the feature description:

"Got it! Planning feature: $ARGUMENTS"

Store this description for use in later phases.

If no argument provided ($ARGUMENTS is empty):

Prompt the user for a detailed feature description using AskUserQuestion:

"Let's start planning a new feature! Please describe what you want to build."

  • Header: "Feature Description"
  • Question: "Describe the feature you want to build. Include what problem it solves, key functionality, and any important constraints. The more detail you provide, the better the planning will be."
  • Options:
    • Quick example: "A user authentication system with OAuth2 support"
    • Detailed example: "An e-commerce checkout flow with payment processing, cart management, shipping options, and order confirmation emails"

The user can also type their own description in the free text field.

Store the description for use throughout all phases.


Phase 2/7: Setup

Generate Directory Name

From the feature description, extract key concepts and generate a directory name:

  1. Identify 2-4 key words/concepts from the description
  2. Convert to kebab-case
  3. Keep it concise (max 30 characters)

Read the full file on GitHub · 506 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. 3d ago First seen · 506 lines · 11 tokens per session scan A 726066fcda35

Subscribe to this mod's changes

feature-planning is a command published in the GitHub repository jsegov/shipspec-claude-code-plugin (20 stars, last pushed 7mo ago), licensed MIT. It adds 11 tokens to every session and 3,805 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.