companion-architecture

companion-architecture is an agent for Claude Code from Matt-Dionis/claude-code-configs. It costs 29 tokens per session (5,913 once invoked), scanned A, original, MIT.

An architecture guide for AI companion services used by multiple customers or organizations. It covers how to model companions, control their abilities, isolate customer data, manage their lifecycle, and scale the service.

In plain words
What is it for?
Use it when designing a multi-tenant AI companion product, including its data model, security boundaries, permissions, memory rules, and scaling approach.
Why use it?
It helps prevent one customer’s data or settings from being mixed with another’s. It also provides a structure for managing companion behavior, permissions, memory, and deployment needs.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the TodoWrite tool.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { db } from "../db/client";.

Good fit Use it when designing a multi-tenant AI companion product, including its data model, security boundaries, permissions, memory rules, and scaling approach.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Matt-Dionis/claude-code-configs
agentmods
npx agentmods add agents/matt-dionis/claude-code-configs/companion-architecture

Made for: Claude Code.

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 companion-architecture

README.md
[![agentmods](https://agentmods.dev/badge/agents/matt-dionis/claude-code-configs/companion-architecture/github.svg)](https://agentmods.dev/agents/matt-dionis/claude-code-configs/companion-architecture)
Your own site
<a href="https://agentmods.dev/agents/matt-dionis/claude-code-configs/companion-architecture"><img src="https://agentmods.dev/badge/agents/matt-dionis/claude-code-configs/companion-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.

agentmods 80×15 button for companion-architecture

Your own site · 80×15
<a href="https://agentmods.dev/agents/matt-dionis/claude-code-configs/companion-architecture"><img src="https://agentmods.dev/badge/agents/matt-dionis/claude-code-configs/companion-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,913 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.
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 $0.00029 $0.05913
Opus 5 $0.00015 $0.02957
Sonnet 5 $0.00006 $0.01183
Haiku 4.5 $0.00003 $0.00591

Measured 10d ago against content hash 72f39ac3fca2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

companion-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.

configurations/mcp-servers/memory-mcp-server/.claude/agents/companion-architecture.md · 894 lines

How it starts

The opening of the file, as written. The whole thing — 894 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert in designing multi-tenant architectures for AI companions, focusing on isolation, security, and scalability for production companion services.

Companion System Architecture

Core Domain Model

// src/domain/companion.ts
export interface Companion {
  id: string;
  name: string;
  description: string;
  ownerId: string; // Organization or user that owns this companion
  
  // Companion personality and behavior
  personality: {
    traits: string[];
    tone: "professional" | "friendly" | "casual" | "formal";
    responseStyle: "concise" | "detailed" | "conversational";
  };
  
  // AI Configuration
  aiConfig: {
    model: string;
    temperature: number;
    maxTokens: number;
    systemPrompt: string;
    knowledgeCutoff?: string;
  };
  
  // Capabilities and permissions
  capabilities: {
    canAccessInternet: boolean;
    canExecuteCode: boolean;
    canAccessFiles: boolean;
    allowedTools: string[];
    memoryRetentionDays: number;
    maxMemoriesPerUser: number;
  };
  
  // Multi-tenancy
  tenancy: {
    isolationLevel: "strict" | "shared" | "hybrid";
    dataResidency?: string; // Geographic location for data
    encryptionKeyId?: string; // For tenant-specific encryption
  };
  
  // Usage and limits
  limits: {
    maxDailyInteractions: number;
    maxConcurrentSessions: number;
    maxMemoryStorage: number; // In MB
    rateLimitPerMinute: number;
  };
  
  // Lifecycle
  status: "active" | "paused" | "archived" | "deleted";
  version: string;
  createdAt: Date;
  updatedAt: Date;
  lastActiveAt?: Date;
}

// User-Companion relationship
export interface CompanionUser {
  companionId: string;
  userId: string;
  
  // Relationship metadata
  relationship: {
    firstInteraction: Date;
    lastInteraction: Date;
    interactionCount: number;
    trustLevel: number; // 0-100
  };
  
  // User-specific companion settings
  preferences: {
    nickname?: string;
    preferredLanguage?: string;
    timezone?: string;
    customSettings?: Record<string, any>;
  };
  
  // Access control
  permissions: {
    canRead: boolean;
    canWrite: boolean;
    canDelete: boolean;
    isBlocked: boolean;
  };
  
  // Usage tracking
  usage: {
    tokensUsed: number;
    memoriesCreated: number;
    lastMemoryAt?: Date;
  };
}

Read the full file on GitHub · 894 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. 10d ago First seen · 894 lines · 29 tokens per session scan A 72f39ac3fca2

Subscribe to this mod's changes

companion-architecture is an agent published in the GitHub repository Matt-Dionis/claude-code-configs (624 stars, last pushed 1y ago), licensed MIT. It adds 29 tokens to every session and 5,913 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

Power Platform MCP Integration Expert

Expert in Power Platform custom connector development with MCP integration for Copilot Studio - comprehensive knowledge of schemas, protocols, and integration patterns.

github/awesome-copilot · 31 tokens

php-developer

Write idiomatic PHP code with design patterns, SOLID principles, and modern best practices. Implements PSR standards, dependency injection, and comprehensive testing. Use PROACTIVELY for PHP architecture, refactoring, or implementing design patterns.

davepoon/buildwithclaude · 51 tokens

backend-reviewer

Use when reviewing service-layer logic, module boundaries, business rules, or cross-service contracts — verifies architecture integrity and service correctness against the api and architect persona standards.

jeremylongshore/tons-of-skills-marketplace · 36 tokens

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 106 tokens

gate

API quality gates — linting, style enforcement, breaking change CI, and API governance.

tonone-ai/tonone · 19 tokens

dotnet-architecture-reviewer

Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…

StefanTheCode/dotnet-ai-toolkit · 102 tokens