new-project

new-project is a skill for Claude Code, Codex from andrewcigan/vibe-dev-plugin. It costs 56 tokens per session (2,137 once invoked), scanned A, original, MIT.

A guided start for a new software project. It collects basic product information, creates the project’s working documents, and chooses a shorter or fuller working process.

In plain words
What is it for?
Use it to name and classify a project, answer an initial business interview, create its starting files, and select a FAST or FULL mode.
Why use it?
Starting without shared decisions can lead to unclear goals and inconsistent work. This gives the project a documented starting point.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the vibe-dev plugin — 29 skills, 24 agents, 7 hooks 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 skills/andrewcigan/vibe-dev-plugin/new-project
Any agent
npx skills add andrewcigan/vibe-dev-plugin --skill new-project
Clone the repo
git clone --depth 1 https://github.com/andrewcigan/vibe-dev-plugin

Made for: Claude Code, Codex.

Or install vibe-dev, the plugin that ships this one along with the rest of its 29 skills, 24 agents, 7 hooks.

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 new-project

README.md
[![agentmods](https://agentmods.dev/badge/skills/andrewcigan/vibe-dev-plugin/new-project.svg)](https://agentmods.dev/skills/andrewcigan/vibe-dev-plugin/new-project)
Your own site
<a href="https://agentmods.dev/skills/andrewcigan/vibe-dev-plugin/new-project"><img src="https://agentmods.dev/badge/skills/andrewcigan/vibe-dev-plugin/new-project.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,137 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 $0.00056 $0.02137
Opus 5 $0.00028 $0.01069
Sonnet 5 $0.00011 $0.00427
Haiku 4.5 $0.00006 $0.00214

Measured 5d ago against content hash 9f1006f3848c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

new-project 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 5d 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.

skills/new-project/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/new-project

Запускает старт нового проекта по Vibe Dev архитектуре.

Что происходит

Шаг 0: Проверка портрета (как с тобой общаться)

Проверь, есть ли файл ~/.vibe-dev/portrait.md. Если НЕТ — это первый запуск; предложи одной фразой, не навязывая:

Прежде чем строить — за минуту настрою, как мне с тобой разговаривать (6 коротких вопросов, разово). Сделать сейчас (/setup) или пропустить и работать на стандартном стиле?

  • Согласен → запусти /setup, затем вернись к Шагу 1.
  • Пропускает / портрет уже есть → сразу к Шагу 1 (без портрета работает нейтральный дефолт medium).

Шаг 1: Подтверждение и выбор папки

Спроси у пользователя:

  1. Название проекта (kebab-case, для папки) — ОДИН вопрос
  2. Тип проекта (для выбора режима): «маркет-продукт / внутренний инструмент / эксперимент-пэт» — ОДИН вопрос

По ответу определяй режим:

  • market product → FULL (10 этапов)
  • внутренний / эксперимент / уверен в стеке → FAST (5 этапов)

Шаг 2: Создать папку и harness bootstrap

cd <рабочая-папка>
mkdir <project-name>
cd <project-name>

# Скопировать 4 стартовых файла из templates/
cp ${CLAUDE_PLUGIN_ROOT}/templates/CLAUDE.md ./CLAUDE.md
cp ${CLAUDE_PLUGIN_ROOT}/templates/feature_list.json ./feature_list.json
cp ${CLAUDE_PLUGIN_ROOT}/templates/SESSION.md ./SESSION.md
cp ${CLAUDE_PLUGIN_ROOT}/templates/domain-rules.yaml ./domain-rules.yaml

# Harness-метка движка: новый проект рождается на актуальном движке = strict by default (H2).
# Проекты без этой метки = legacy (структурные проверки warn, UI-evidence всё равно hard),
# переводятся на strict командой /upgrade-project.
# Двухфазная активация (v6.2 F2): пишем pending-strict — в боевой strict переведёт ТОЛЬКО
# живой хук на следующем сообщении (факт перевода = доказательство, что enforcement активен).
# Если профиль остался pending-strict — хуки НЕ работают: НЕ продолжай молча, чини активацию (/doctor).
mkdir -p .harness
# Пин на АКТУАЛЬНЫЙ мажор плагина (динамически — новый проект не должен сам себе слать «обновись»).
echo "$(jq -r '.version // "7"' "${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json" 2>/dev/null | cut -d. -f1).0" > .harness/engine-version
echo "pending-strict" > .harness/profile

# Создать стандартный .gitignore сразу (closes security gap)
cat > .gitignore <<'EOF'
node_modules/
.env
.env.*
*.pem
*.key
secrets/
.harness/cost-log.json
.harness/tools-audit.jsonl
.harness/locks/
.DS_Store
EOF

# Init git
git init -q

# Pre-commit backstop (v6.2 F2): activation-страж + WIP=1 scope. Независимый канал —
# блокирует коммиты, если профиль строгости заявлен, а живые хуки не работают.
bash "${CLAUDE_PLUGIN_ROOT}/scripts/install-precommit.sh" "$(pwd)"

git add .
git commit -q -m "init: vibe-dev harness bootstrap"

Read the full file on GitHub · 182 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. 5d ago First seen · 182 lines · 56 tokens per session scan A 9f1006f3848c

Subscribe to this mod's changes

new-project is a skill published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 2,137 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

harness

하네스를 구성합니다. 전문 에이전트를 정의하며, 해당 에이전트가 사용할 스킬을 생성하는 메타 스킬. (1) '하네스 구성해줘', '하네스 구축해줘' 요청 시, (2) '하네스 설계', '하네스 엔지니어링' 요청 시, (3) 새로운 도메인/프로젝트에 대한 하네스 기반 자동화 체계를 구축할 때, (4) 하네스 구성을 재구성하거나 확장할 때, (5) '하네스 점검', '하네스 감사', '하네스 현황', '에이전트/스킬 동기화' 등 기존 하네스 운영/유지보수 요청 시 사용.

revfactory/harness · 170 tokens

kimchi

Turn a raw product idea into build-ready docs — one doc per EPIC with locked decisions, exact API contracts, a story-by-story priority plan, and an execute.md handoff Claude can build from across sessions. Gets the clarity by interrogating the user through a roster of expert personas that grill, counter, and refuse to…

chitransh-cj/kimchi · 122 tokens

compose

The mumei orchestrator. For new features, presents a vehicle picker — spec (full SDD workflow: clarification → requirements → design → tasks each auto-reviewed up to 3 iterations → single user approval → Wave-by-Wave implementation → 4-stage review) or plan (Claude Code plan-mode wrapper: hand off to plan mode…

iroha924/mumei · 213 tokens

peruse

Plan-vehicle review pipeline. Runs Stage 0 detector (semgrep + osv-scanner) plus security-reviewer and adversarial-reviewer in parallel against the current diff, validates each finding via issue-validator, aggregates a verdict, and writes a review JSON to .mumei/plans/ /reviews/ .json. Triggers when the user invokes…

iroha924/mumei · 160 tokens

release

Release a new version of the mumei repository. Invoke when the user gives an explicit release instruction ("release it", "/release", "patch release", "ship 0.2.0"). Takes no argument or "patch" / "minor" / "major" for a SemVer bump, or a direct version such as "0.2.0". Wraps any uncommitted changes into a single…

iroha924/mumei · 144 tokens

glean

This skill should be used BEFORE any feature design. It runs structured gleaning with the user — asking 5 high-leverage questions per round, up to 3 rounds, to extract Goal / Scope / Constraints / Edges / Done. Output is saved to .mumei/scratch/ .md and used as input for /mumei:compose. Triggers include "I want to add…

iroha924/mumei · 107 tokens