feature-dev

A seven-step workflow for building a software feature, from understanding the request and exploring the code to designing, coding, reviewing, and summarising the work.

In plain words
What is it for?
Use it to take a feature from an initial idea through codebase investigation, design, implementation, quality review, and a final summary.
Why use it?
It prevents important planning or review steps from being skipped and keeps feature work in a clear order.

Command

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/sequenzia/claude-plugins/feature-dev
Clone the repo
git clone --depth 1 https://github.com/sequenzia/claude-plugins
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 2,539 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 $0.00013 $0.02539
Opus 5 $0.00006 $0.01269
Sonnet 5 $0.00003 $0.00508
Haiku 4.5 $0.00001 $0.00254

Measured yesterday against content hash 9912f0b1c786, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-dev 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.

plugins/dev-tools/commands/feature-dev.md · 358 lines

How it starts

The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Development Workflow

You are executing a structured 7-phase feature development workflow. This workflow guides you through understanding, exploring, designing, implementing, and reviewing a feature.

CRITICAL: You MUST complete ALL 7 phases. The workflow is not complete until Phase 7: Summary is finished. After completing each phase, immediately proceed to the next phase without waiting for user prompts.

Phase Overview

Execute these phases in order, completing ALL of them:

  1. Discovery - Understand the feature requirements
  2. Codebase Exploration - Map relevant code areas
  3. Clarifying Questions - Resolve ambiguities
  4. Architecture Design - Design the implementation approach
  5. Implementation - Build the feature
  6. Quality Review - Review for issues
  7. Summary - Document accomplishments

Phase 1: Discovery

Goal: Understand what the user wants to build.

  1. Create a TodoWrite entry for each phase:

    - Phase 1: Discovery
    - Phase 2: Codebase Exploration
    - Phase 3: Clarifying Questions
    - Phase 4: Architecture Design
    - Phase 5: Implementation
    - Phase 6: Quality Review
    - Phase 7: Summary
    
  2. Mark Phase 1 as in_progress

  3. Analyze the feature description:

    • What is the core functionality?
    • What are the expected inputs and outputs?
    • Are there any constraints mentioned?
    • What success criteria can you infer?
  4. Summarize your understanding to the user. Ask if your understanding is correct before proceeding.

  5. Mark Phase 1 as completed


Phase 2: Codebase Exploration

Goal: Understand the relevant parts of the codebase.

  1. Mark Phase 2 as in_progress

  2. Load skills for this phase:

    • Read ${CLAUDE_PLUGIN_ROOT}/skills/project-conventions/SKILL.md and apply its guidance
    • Read ${CLAUDE_PLUGIN_ROOT}/skills/language-patterns/SKILL.md and apply its guidance
  3. Launch code-explorer agents:

    Launch 2-3 code-explorer agents in parallel with different focus areas:

    Agent 1: Explore entry points and user-facing code related to the feature
    Agent 2: Explore data models, schemas, and storage related to the feature
    Agent 3: Explore utilities, helpers, and shared infrastructure (if applicable)
    

Read the full file on GitHub · 358 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 · 358 lines · 13 tokens per session scan A 9912f0b1c786

Subscribe to this mod's changes

feature-dev is a command published in the GitHub repository sequenzia/claude-plugins (2 stars, last pushed 7mo ago), licensed MIT. It adds 13 tokens to every session and 2,539 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 2026-08-31.