feature-build

feature-build is a command for Claude Code from ahmed3elshaer/everything-claude-code-mobile. It costs 45 tokens per session (512 once invoked), scanned A, original, MIT.

An end-to-end command for building a complete mobile feature from a description to verified code. It plans the work, implements it, creates tests, fixes build problems, reviews quality, and checks the result.

In plain words
What is it for?
Use it to build Android, iOS, or shared Kotlin features, resume from a particular phase, or skip the quality phase when needed.
Why use it?
It brings the many steps of mobile feature development into one tracked process. This reduces the chance of forgetting tests, build fixes, quality checks, or final verification.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the everything-claude-code-mobile plugin — 46 skills, 35 commands, 27 agents, 2 hooks, 3 MCP servers 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/ahmed3elshaer/everything-claude-code-mobile/feature-build
Clone the repo
git clone --depth 1 https://github.com/ahmed3elshaer/everything-claude-code-mobile

Made for: Claude Code.

Or install everything-claude-code-mobile, the plugin that ships this one along with the rest of its 46 skills, 35 commands, 27 agents, 2 hooks, 3 MCP servers.

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.

agentmods badge for feature-build

README.md
[![agentmods](https://agentmods.dev/badge/commands/ahmed3elshaer/everything-claude-code-mobile/feature-build.svg)](https://agentmods.dev/commands/ahmed3elshaer/everything-claude-code-mobile/feature-build)
Your own site
<a href="https://agentmods.dev/commands/ahmed3elshaer/everything-claude-code-mobile/feature-build"><img src="https://agentmods.dev/badge/commands/ahmed3elshaer/everything-claude-code-mobile/feature-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 512 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 5.1 $0.00045 $0.00512
Opus 5 $0.00023 $0.00256
Sonnet 5 $0.00009 $0.00102
Haiku 4.5 $0.00005 $0.00051

Measured 2d ago against content hash 98a7cada7d2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

feature-build 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 2d 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-build.md · 61 lines

What it actually says

Feature Build Command

Master entry point for end-to-end mobile feature construction. Runs all 6 phases sequentially, tracking progress in state files.

Usage

/feature-build Add user authentication with biometrics
/feature-build --platform=android Implement offline caching
/feature-build --from-phase=test auth
/feature-build --skip-phase=quality Add profile screen

Flags

Flag Values Description
--platform android, ios, kmp Override auto-detection
--from-phase implement, test, build-fix, quality, verify Resume from a specific phase
--skip-phase quality Skip a phase

Phases

# Phase Command Description
1 Plan /feature-plan Architecture, file breakdown, test strategy
2 Implement /feature-implement Parallel agent implementation
3 Test /feature-test Unit, UI, and E2E test creation
4 Build & Fix /feature-build-fix Compile and fix errors iteratively
5 Quality Gate /feature-quality-gate Code review, security, performance
6 Verify /feature-verify pass@k metrics, coverage, sign-off
7 Learn (automatic) Pattern extraction, instinct updates, completeness scoring

State

Progress tracked in .omc/state/feature-{name}.json. Use /feature-status to inspect.

Examples

# Full feature build with auto-detected platform
/feature-build Add push notification support

# Android-only, skip quality gate for prototype
/feature-build --platform=android --skip-phase=quality Add search screen

# Resume a failed build from the test phase
/feature-build --from-phase=test auth

# KMP feature targeting shared module
/feature-build --platform=kmp Add offline sync for user data

Invokes

  • feature-builder skill (orchestrates all phases)
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. 2d ago First seen · 61 lines · 45 tokens per session scan A 98a7cada7d2a

Subscribe to this mod's changes

feature-build is a command published in the GitHub repository ahmed3elshaer/everything-claude-code-mobile (65 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 512 once invoked, about $0.0002 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 2026-09-03.