feature-dev

A guided workflow for building a software feature, from understanding the request through research, design, implementation, review, and documentation. It emphasizes clarifying questions and learning the project's existing patterns first.

In plain words
What is it for?
Use it when developing a new feature or component and you want a structured process for requirements, design decisions, coding, review, and progress tracking.
Why use it?
It reduces the risk of building the wrong thing or adding code that does not fit the rest of the project.

Command for Claude Code

Part of the feature-dev plugin — 1 command, 3 agents 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/opensesh/karimo-overview/feature-dev
Clone the repo
git clone --depth 1 https://github.com/opensesh/karimo-overview

Made for: Claude Code.

Or install feature-dev, the plugin that ships this one along with the rest of its 1 command, 3 agents.

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 1,682 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 $0.01682
Opus 5 $0.00005 $0.00841
Sonnet 5 $0.00002 $0.00336
Haiku 4.5 $0.00001 $0.00168

Measured 3d ago against content hash b1fb91fb99f9, 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 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.

.claude/plugins/feature-dev/commands/feature-dev.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Development

A systematic 7-phase workflow that helps you build features thoughtfully — from understanding to implementation to review.

You're helping build a new feature or component. Follow this approach: understand first, ask questions, design elegantly, then implement.

For Designers

This workflow mirrors the design process you already know:

  1. Discovery → Understand the brief
  2. Research → Explore existing patterns
  3. Define → Clarify requirements
  4. Design → Choose an approach
  5. Build → Implement with care
  6. Review → Check quality
  7. Document → Summarize the work

Core Principles

  • Ask clarifying questions — Don't assume. Ask specific, concrete questions and wait for answers before implementing.
  • Understand before acting — Read and comprehend existing patterns first. For BOS projects, understand our design tokens and component patterns.
  • Simple and elegant — Prioritize readable, maintainable code that follows our warm neutrals philosophy.
  • Use TodoWrite — Track progress throughout so you can see where you are.

Phase 1: Discovery

Goal: Understand what we're building

Initial request: $ARGUMENTS

Actions:

  1. Create a todo list with all phases
  2. If the feature is unclear, ask:
    • What problem are we solving? Who is this for?
    • What should this feature do? What's the happy path?
    • Any constraints? Performance, accessibility, existing patterns to match?
  3. Summarize your understanding and confirm it's correct

Designer tip: Think of this like the creative brief. Get clear on the "why" before the "what."


Phase 2: Codebase Exploration (Research)

Goal: Understand how similar things work in the codebase

Actions:

  1. Launch 2-3 explorer agents to investigate:

    • Similar features or components
    • Overall architecture and patterns
    • UI patterns and styling approaches

    Example prompts:

    • "Find components similar to [feature] and trace how they're built"
    • "Map the design system patterns used in [area]"
    • "Analyze how [existing component] handles state and styling"

Read the full file on GitHub · 249 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 · 249 lines · 11 tokens per session scan A b1fb91fb99f9

Subscribe to this mod's changes

feature-dev is a command published in the GitHub repository opensesh/karimo-overview (11 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 1,682 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.