A complete eight-phase workflow for developing a software feature, from understanding the request through implementation and review. It can use separate specialist agents when the feature-dev plugin is installed.

Use it to guide a feature from initial clarification and architecture through coding, testing, and quality review, optionally in a separate worktree.

It gives feature work a defined sequence and checkpoints instead of leaving discovery, design, coding, and review disconnected.

dev:feature — Skill for Claude Code by atournayre

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.

Any agent

npx skills add atournayre/claude-marketplace --skill feature

Clone the repo

git clone --depth 1 https://github.com/atournayre/claude-marketplace

Made for: Claude Code.

Or install dev, the plugin that ships this one along with the rest of its 25 skills, 8 agents.

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/skills/atournayre/claude-marketplace/feature/github.svg)](https://agentmods.dev/skills/atournayre/claude-marketplace/feature)

Your own site

<a href="https://agentmods.dev/skills/atournayre/claude-marketplace/feature"><img src="https://agentmods.dev/badge/skills/atournayre/claude-marketplace/feature/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/atournayre/claude-marketplace/feature"><img src="https://agentmods.dev/badge/skills/atournayre/claude-marketplace/feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,836 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	$0.00010	$0.01836
Opus 5	$0.00005	$0.00918
Sonnet 5	$0.00002	$0.00367
Haiku 4.5	$0.00001	$0.00184

Measured 11d ago against content hash 492ebd78bec2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dev:feature 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 11d 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.

dev/skills/feature/SKILL.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Objectif

Orchestrateur du workflow de développement en 8 phases. Enchaîne automatiquement toutes les étapes avec des checkpoints utilisateur.

Feature demandée

$ARGUMENTS

Prérequis

⚠️ Plugin feature-dev requis pour les agents spécialisés.

Si non installé, afficher :

⚠️ Pour une expérience optimale, installe le plugin feature-dev :
/plugin install feature-dev@claude-code-plugins

Ce plugin fournit les agents :
- code-explorer (exploration codebase)
- code-architect (design architecture)
- code-reviewer (review qualité)

Continuer sans ces agents ? (Les phases 1, 3, 6 seront simplifiées)

Instructions à Exécuter

IMPORTANT : Exécute ce workflow étape par étape :

Initialisation

1. Proposition de worktree (optionnel)

Utilise AskUserQuestion pour demander à l'utilisateur s'il souhaite créer un worktree pour cette feature :

📂 Créer un worktree pour cette feature ?

Avantages des worktrees :
  • Garder votre branche main propre
  • Travailler sur plusieurs features en parallèle
  • Préserver le contexte de développement (IDE, serveur, tests)
  • Pas besoin de stash ou de switcher de branche

Le worktree sera créé dans : .worktrees/{feature-slug}

Créer le worktree ? (o/n)

Si oui :

Normaliser le nom de la feature en slug (kebab-case)
Créer le worktree avec /dev:worktree create {feature-slug}
Informer l'utilisateur du chemin et qu'il doit relancer Claude Code dans le worktree

ARRÊTER le workflow avec un message :

✅ Worktree créé : .worktrees/{feature-slug}

Pour continuer le workflow :
  1. cd .worktrees/{feature-slug}
  2. Relancer Claude Code
  3. /dev:feature {description}

Si non : Continuer le workflow normalement.

Créer le fichier .claude/data/.dev-workflow-state.json (créer le répertoire .claude/data/ si nécessaire)
Créer les tâches du workflow

Utiliser TaskCreate pour chaque phase :

TaskCreate #0: Discover - Comprendre le besoin
TaskCreate #1: Explore - Explorer codebase
TaskCreate #2: Clarify - Questions clarification
TaskCreate #3: Design - Proposer architectures
TaskCreate #4: Plan - Générer specs
TaskCreate #5: Code - Implémenter
TaskCreate #6: Review - QA complète
TaskCreate #7: Summary - Résumé final
TaskCreate #8: Cleanup - Nettoyer worktree (si créé)

Read the full file on GitHub · 212 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.

11d ago First seen · 212 lines · 10 tokens per session scan A 492ebd78bec2

Subscribe to this mod's changes

dev:feature is a skill published in the GitHub repository atournayre/claude-marketplace (9 stars, last pushed 6mo ago), licensed MIT. It adds 10 tokens to every session and 1,836 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.

Planning

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens