What is vibe-architecture?

A set of architecture rules for software projects that adjusts its guidance to the project's risk tier. It uses an intake questionnaire and applies security, reliability, and development practices while code is written.

Use it when creating or changing an app, website, or API, especially when choosing an architecture or applying security and reliability practices.

It helps prevent important design, security, and deployment concerns from being overlooked when building software.

vibe-architecture — Skill for Claude Code and Codex by jgnoonan

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 jgnoonan/vibeArchitecture --skill vibe-architecture

Clone the repo

git clone --depth 1 https://github.com/jgnoonan/vibeArchitecture

Made for: Claude Code, Codex.

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/jgnoonan/vibearchitecture/vibe-architecture/github.svg)](https://agentmods.dev/skills/jgnoonan/vibearchitecture/vibe-architecture)

Your own site

<a href="https://agentmods.dev/skills/jgnoonan/vibearchitecture/vibe-architecture"><img src="https://agentmods.dev/badge/skills/jgnoonan/vibearchitecture/vibe-architecture/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/jgnoonan/vibearchitecture/vibe-architecture"><img src="https://agentmods.dev/badge/skills/jgnoonan/vibearchitecture/vibe-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,613 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Rogue Agent · line 143
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

How audits are shown

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	$0.00042	$0.02613
Opus 5	$0.00021	$0.01307
Sonnet 5	$0.00008	$0.00523
Haiku 4.5	$0.00004	$0.00261

Measured 10d ago against content hash c8510e13e047, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

vibe-architecture 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 10d 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.

ClaudeSkill/vibe-architecture/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vibeArchitecture

Framework version: 1.5.0

Architectural guardrails for AI-generated code. When the user asks you to build software, follow this skill's instructions to ensure the code is secure, reliable, and production-ready.

When to Activate

Activate this skill when:

The user asks you to build an app, website, API, or any software project
The user asks you to write code for a new or existing project
The user mentions "vibeArchitecture" by name
The user asks about security, architecture, or deployment best practices for their project

Step 1: Check for an Existing Project Profile

Look for a PROJECT_PROFILE.md in the project root or in the conversation context.

If it exists and is filled in (tier and project basics resolved) and experience_level is one of beginner, intermediate, or experienced: Read the tier and apply the rules for that tier. Skip to Step 3.
If it exists and is filled in but experience_level is missing or invalid: Do not write code yet. Ask once: "How do you want explanations: short and technical, or step by step with more context?" Map to experienced / beginner / intermediate respectively; if the user skips, default to experienced and note they can say "explain like I'm new" anytime. Update PROJECT_PROFILE.md, then go to Step 3.
If it does not exist or has placeholder text: Proceed to Step 2.

Step 2: Run the Intake Conversation

Before writing any code, ask the user these questions conversationally. Ask one or two at a time. Be natural, not interrogative.

Start with: "Before we start building, I'd like to ask a few quick questions about your project. This helps me apply the right level of protection. Takes about 5 minutes."

Q0: "What's your background with building software?" — new to this (AI does most of the coding) → beginner; built a few things (can read and change code) → intermediate; experienced developer → experienced. Record as experience_level. This changes communication style only, not which rules apply.

Read the full file on GitHub · 185 lines

Files

What ships with it

17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

10d ago First seen · 185 lines · 42 tokens per session scan A c8510e13e047

Subscribe to this mod's changes

vibe-architecture is a skill published in the GitHub repository jgnoonan/vibeArchitecture (21 stars, last pushed 9d ago), licensed MIT. It adds 42 tokens to every session and 2,613 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 2026-08-30.

Planning Security

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