Borrowing it
Nothing to install: this file belongs to radif-ru/ai-multi-agent-system. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/radif-ru/ai-multi-agent-system/main/.agents/skills/architecture-discipline/SKILL.mdgit clone --depth 1 https://github.com/radif-ru/ai-multi-agent-systemWrote 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.
[](https://agentmods.dev/skills/radif-ru/ai-multi-agent-system/architecture-discipline)<a href="https://agentmods.dev/skills/radif-ru/ai-multi-agent-system/architecture-discipline"><img src="https://agentmods.dev/badge/skills/radif-ru/ai-multi-agent-system/architecture-discipline/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.
<a href="https://agentmods.dev/skills/radif-ru/ai-multi-agent-system/architecture-discipline"><img src="https://agentmods.dev/badge/skills/radif-ru/ai-multi-agent-system/architecture-discipline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00054 | $0.00798 |
| Opus 5 | $0.00027 | $0.00399 |
| Sonnet 5 | $0.00011 | $0.00160 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
architecture-discipline 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: architecture-discipline
Базовые архитектурные правила репозитория. Загружай первым для широкой/неочевидной задачи, затем — профильный скилл. Источник истины — _docs/architecture.md и _docs/instructions.md §11.
Когда использовать
- Задача широкая или неочевидная — начни отсюда, чтобы выбрать следующий скилл.
- Добавляешь компонент или поток, трогаешь границы слоёв, реестр tools, память или агентный цикл.
- Сомневаешься, не выходит ли решение за рамки уже принятой архитектуры.
Алгоритм
- Слоистая изоляция. Поток: адаптер (
app/adapters/) → core (app/core/orchestrator.py) → executor (app/agents/) → tools / LLM / memory (app/tools/,app/services/). Слой ниже не знает про слой выше: tool не знает про aiogram, memory — про executor, executor — про Telegram. - Единая точка входа. Любой адаптер вызывает только
core.handle_user_task(...). Адаптер не дёргаетExecutor/Planner/Criticнапрямую. - JSON-only цикл. Ответ LLM в агентном цикле — строго JSON одной из форм
_docs/agent-loop.md. Prose-ответ в цикле считается ошибкой. - Tools as a registry. Новый tool — отдельный модуль с контрактом
name/description/args_schema/async run(args, ctx), регистрация вapp/tools/registry.py(_docs/tools.md). - Memory split. Краткосрочная — in-memory
ConversationStore; долгосрочная —sqlite-vec(SemanticMemory), пополняется только саммари при/new, не сырыми сообщениями (_docs/memory.md). - Local-first, без облака. Только локальная Ollama; единственная БД —
sqlite-vec; polling, не webhook (_docs/instructions.md§11). - Async-first. Любой I/O — через
await; общие клиенты создаются один раз на приложение → скиллasync-discipline. - Без новой архитектуры без согласования. Новый слой/сервис/абстракция/паттерн/зависимость или смена структуры каталогов — сначала проговорить с пользователем (
_docs/instructions.md§11). В рамках задачи — только локальные технические решения.
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.
- 12d ago First seen · 38 lines · 54 tokens per session scan A d73136b61c8f
architecture-discipline is a skill published in the GitHub repository radif-ru/ai-multi-agent-system (6 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 798 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.
Other skills, from other repositories
ai-portable-setup
Erstellt einen portablen KI-Arbeitsbereich auf einem USB-Stick oder beliebigen Laufwerk. RAG-Pipeline mit lokalen LLM-Modellen (Ollama), Vektordatenbank (ChromaDB) und vorkonfigurierten Prompts.
ai-image-color-cycling
Generate an AI image, quantize it to a 256-color indexed palette, and produce BOTH a self-contained HTML artifact AND a perfect-loop animated GIF that bring the image to life via classic 1990s palette cycling — the trick where rotating palette entries makes water flow, fire flicker, and stars twinkle without ever…
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.