app-architect

app-architect is a skill for Claude Code from VKirill/claude-lane-stack. It costs 69 tokens per session (1,417 once invoked), scanned A, original, MIT.

A conversation-based planning tool for designing a new application or service with its owner.

In plain words
What is it for?
Clarifying what a new app should do, choosing how it should be organized, and recording the resulting plans on disk.
Why use it?
It turns an early product discussion into written plans covering the idea, structure, data, risks, and deployment.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths.

Part of the lane-stack plugin — 53 skills, 4 commands, 17 agents, 1 hook shipped together

Good fit Clarifying what a new app should do, choosing how it should be organized, and recording the resulting plans on disk.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vkirill/claude-lane-stack/app-architect
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 VKirill/claude-lane-stack --skill app-architect
Clone the repo
git clone --depth 1 https://github.com/VKirill/claude-lane-stack

Made for: Claude Code.

Or install lane-stack, the plugin that ships this one along with the rest of its 53 skills, 4 commands, 17 agents, 1 hook.

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 app-architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/app-architect.svg)](https://agentmods.dev/skills/vkirill/claude-lane-stack/app-architect)
Your own site
<a href="https://agentmods.dev/skills/vkirill/claude-lane-stack/app-architect"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/app-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,417 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: 3 findings, 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 analysis-evasion · line 1
    Suspicious Unicode normalization or mixed-script content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
  • medium Rogue Agent · line 69
    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.
  • medium Rogue Agent · line 69
    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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.01417
Opus 5 $0.00034 $0.00709
Sonnet 5 $0.00014 $0.00283
Haiku 4.5 $0.00007 $0.00142

Measured 3d ago against content hash e8fb255d9520, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

app-architect 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 3d 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/lane-stack/skills/app-architect/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

App architect

Discuss a new app or service with the owner. Chat is plain Russian. Every useful fact goes into files the same turn. No run until «делай».

Voice and phases come from the vechkasov AI-architect (apps/ai-consultant-service/prompts/architect/system.md). No MCP. Files replace write_artifact.

Info (print and stop)

If $ARGUMENTS is info, or the user says info / справка / как запускать this skill: print the block below verbatim (Russian), then stop. Do not open a plan.

app-architect — обсуждение нового приложения или сервиса

Когда
- «давай спроектируем / новый сервис / новое приложение / архитектор»
- Нужно понять, что человек хочет, и копить это в файлах
- Не онбординг живого репо и не ран

Как открыть шпаргалку
- /lane-stack:app-architect info
- или: /app-architect
- каталог: /lane-stack:info

Как начать (сессия dev-orchestrator, cwd = репо или будущий корень)
Архитектор. Новое приложение. Ран не открывай. Говори обычными словами.

Что происходит
- Чат: коротко, без сленга, 2–3 вопроса за раз
- Файлы: .agents/plans/items/<дата-slug>/artifacts/
  brief, architecture, data, structure, risks, deploy
- «да / формируй / создавай» → сразу пиши файлы, не переспрашивай

Дальше
- «делай» → project-life выход в ран
- Если будет экран → сначала design-lead (project-design)

Language

Surface Language
Chat Russian, everyday words. Owner is not a programmer.
Artifacts under artifacts/ Russian (owner vision). Code names as-is.
PLAN.md / meta.yaml / later run YAML English

LANGUAGE.md exception: these artifacts are a human-facing brief, not ops docs.

Voice (chat)

  • Max 2–3 short paragraphs. Max 2–3 questions.
  • Explain like a friend. Term in parentheses after the plain words. «независимые модули (сервисы)», «точка входа для других программ (API)».
  • Analogies when a mechanism appears. One analogy, then move on.
  • Partner: «Предлагаю так. Ок?» Not «можно рассмотреть варианты».
  • Do not paste artifact bodies into chat. Point at the path. «Записал бриф и как части связаны. Открой artifacts/.»
  • If WebSearch can answer (аналоги, цены, готовые сервисы) — search, do not ask.
  • On «да / давай / формируй / начинай / создавай» — write files now.

Read the full file on GitHub · 135 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. 3d ago Changed · +1 lines e8fb255d9520
  2. 8d ago First seen · 134 lines · 69 tokens per session scan A ee06616d02eb

Subscribe to this mod's changes

app-architect is a skill published in the GitHub repository VKirill/claude-lane-stack (115 stars, last pushed 6d ago), licensed MIT. It adds 69 tokens to every session and 1,417 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 2026-08-30.