agentmods.dev

start-project

A project-starting skill that reads a PRD, or product requirements document, and uses it to set up a project according to the agentic-base standard. It records the project's goals and limits in CLAUDE.md.

In plain words
What is it for?
It extracts the purpose, scope, users, success criteria, and constraints from a PRD, then identifies required agent roles and updates the project's instruction file.
Why use it?
It gives the agent a written reference for the intended product and prevents it from filling gaps in the requirements with guesses. It also asks the user to approve suggested plugins.

Skill for Claude CodeCodex

2 1mo ago A scan 108 tokens original MIT
View the source file boranesn/agentic-base
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/boranesn/agentic-base/start-project
Any agent
npx skills add boranesn/agentic-base --skill start-project
Clone the repo
git clone --depth 1 https://github.com/boranesn/agentic-base

Made for: Claude Code, Codex.

Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,228 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 $0.00108 $0.01228
Opus 5 $0.00054 $0.00614
Sonnet 5 $0.00022 $0.00246
Haiku 4.5 $0.00011 $0.00123

Measured 2d ago against content hash 63a06f969e8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start-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 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.

plugins/core-loop/skills/start-project/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kullanıcı bu skill'i çağırdığında bir PRD ile projeyi agentic-base disiplinine göre kurmak istiyor. Aşağıdaki adımları SIRASIYLA uygula. Hiçbir adımı atlayıp otomatik karar verme; roller konusunda kararı kullanıcıya bırak.

1. PRD'yi al ve oku

  • Kullanıcı PRD dosya yolunu vermediyse iste. Dosyayı Read ile oku.
  • PRD yoksa, boşsa ya da okunamıyorsa DUR ve kullanıcıdan iste — varsayımla proje kurma.

2. Hedef + kapsam özetini çıkar ve CLAUDE.md'ye yaz

  • Şu yapıda kısa bir özet üret: Amaç, Kapsam (dahil / hariç), Ana kullanıcı, Başarı kriterleri, Bilinen kısıtlar.
  • CLAUDE.md zaten varsa önce Read et; içeriğin geri kalanını KORUYARAK ## agentic-base: Proje Çıpası (PRD Özeti) başlıklı bölümü ekle veya güncelle. Yoksa bu bölümle CLAUDE.md'yi oluştur.
  • Bu özet, drift-detection çıpasıdır: uzun görevlerde "hâlâ doğru hedefe mi ilerliyoruz?" kontrolünün referansıdır. Bu yüzden net ve PRD'ye sadık olmalı.
  • DÜRÜSTLÜK: PRD'de olmayan hedef/kapsam/metrik UYDURMA. PRD'nin belirsiz bıraktığı noktaları "PRD'de belirtilmemiş" olarak açıkça işaretle; boşluğu kendi varsayımınla doldurma.
  • Çıpa bölümünün sonuna şu sabit Çalışma disiplini alt bölümünü de ekle: "Önemli kod değişikliklerini ilgili rol-agent'a devret (backend / frontend / database / llm-integration / auth / security); ana oturum orkestrasyon, inceleme ve küçük düzeltmelerle sınırlı kalsın." Bu talimat BAĞLAYICI DEĞİLDİR (hook değil, varsayılan sinyaldir) — deterministik tarafı core-loop'un main-edit dedektörü sağlar: rol-agent kaydı olmadan yapılan ana-oturum kod düzenlemeleri undisciplined_edit_detected olarak loglanır ve kullanıcıya gösterilir.

3. Gerekli rolleri belirle (bu bir ÖNERİ, karar değil)

PRD içeriğine bakarak hangi plugin'lerin gerektiğini GEREKÇESİYLE çıkar:

  • core-loop — her zaman zorunlu (log/gate/confidence çekirdeği).
  • dev-roles — kod yazımı varsa (backend / frontend / veritabanı / LLM entegrasyonu).
  • security-roles — auth, giriş/kayıt, ödeme, kişisel veri, izin/rol yönetimi veya kripto varsa. Bu YÜKSEK RİSKLİ bir plugin'dir (spec ilke 4: yüksek riskli roller ekstra dikkatle, en son devreye alınır) — önerdiğinde bunu ayrıca vurgula.
  • growth-roles — pazarlama, satış, pazar araştırması veya içerik üretimi varsa.

Read the full file on GitHub · 62 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. 2d ago First seen · 62 lines · 108 tokens per session scan A 63a06f969e8b

Subscribe to this mod's changes

start-project is a skill published in the GitHub repository boranesn/agentic-base (2 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 1,228 once invoked, about $0.0005 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.

Building agentsPlanningai-agentsclaude-codeclaude-code-pluginsdeveloper-toolshooksplugin-system
Related

Other skills, from other repositories

shipping-artifacts

The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded…

phuryn/pm-skills · 120 tokens

converter

Convert AgentOps skill formats. Triggers: "converter", "convert agentops skill formats.", "converter skill".

boshu2/agentops · 25 tokens

ms

Skill "ms" from boshu2/agentops, covering ms — metaskill search/load engine, constraints, quick start, consume — mcp-primary (mcpms) and write / admin — cli-only (verified landing in the live db).

boshu2/agentops · 65 tokens

skill-builder

Create a metadata-complete AgentOps skill source package, regenerate its derived projections, and check or repair structural hygiene in skill packages. Triggers: "create a skill", "scaffold skill", "absorb external skill", "new skill", "heal skill", "repair skill hygiene", "audit skill structure", "check skill…

boshu2/agentops · 71 tokens

swarm

Dispatch explicit disjoint packets exactly once through a caller-selected executor. Triggers: "swarm", "dispatch disjoint packets", "parallel explicit tasks".

boshu2/agentops · 34 tokens

coding-agents-hooks-authoring

To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.

griddynamics/rosetta · 31 tokens