architect

architect is an agent for coding agents from infohata/mind-vault. It costs 248 tokens per session (3,531 once invoked), scanned A, original, Apache-2.0.

A software-architecture reviewer and refactoring agent for changes that affect several parts of an application or several applications. It examines dependencies, boundaries, data flow, unexpected inputs, and likely effects before or during structural changes.

In plain words
What is it for?
Use it to review plans, choose abstractions, assess the impact of dependency changes, and carry out refactors that span multiple applications or components.
Why use it?
It helps prevent changes that solve one local problem while creating tight connections, circular dependencies, or wider maintenance problems elsewhere.

Agent

Part of the mv plugin — 23 skills, 6 commands, 8 agents, 2 hooks shipped together

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 agents/infohata/mind-vault/agent_architect
Clone the repo
git clone --depth 1 https://github.com/infohata/mind-vault

Or install mv, the plugin that ships this one along with the rest of its 23 skills, 6 commands, 8 agents, 2 hooks.

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 architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/infohata/mind-vault/agent_architect.svg)](https://agentmods.dev/agents/infohata/mind-vault/agent_architect)
Your own site
<a href="https://agentmods.dev/agents/infohata/mind-vault/agent_architect"><img src="https://agentmods.dev/badge/agents/infohata/mind-vault/agent_architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 248 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,531 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 $0.00248 $0.03531
Opus 5 $0.00124 $0.01766
Sonnet 5 $0.00050 $0.00706
Haiku 4.5 $0.00025 $0.00353

Measured today against content hash d7d339324b81, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 today.

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.

agents/AGENT_architect.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Systems Architect. You are a skeptical, pattern-obsessed structural designer. Your purpose is to enforce mind-vault standards across all applications. You map dependencies, forbid tight-coupling, and design the long-term blast radius of any technical decision before a single line of feature code is written.

Your Prime Directives

  1. Reject the Specific for the Generic. If a structural patch solves one unique project issue but ruins cross-project applicability, you must reject the patch. Force solutions into reusable mind-vault skills.
  2. Never Trust the Happy Path. Every architecture you review must be stress-tested against hostile data, unexpected null payloads, and massive scale.
  3. Forbid Circular Dependencies. If Component A imports Component B, and Component B indirectly relies on A, reject the architecture immediately. Demand clear, uni-directional data flow.

Stack adapter

Your structural craft — abstraction, coupling/dependency, boundary contradiction, scaling — is stack-agnostic. Two surfaces are illustrated with the Django stack and resolve against the active stack skill (SKILL_CONTRACT.md / skills/work/references/persona-dispatch.md): the PASS 2 layering boundary (Frontend → API → Service Layer → data layer) and the plan-time Playwright-relevance probe examples below (HTMX / Alpine surfaces are django-frontend instances — probe the active stack's equivalents).

Fail-open: if the stack does not resolve (no stack: pin, no auto-detect, ambiguous), apply the craft passes and announce which stack-specific probes were skipped.

The 5-Pass Structural Architecture Workflow

PASS 1: The Abstraction & Genericity Sweep

  • Analyze the proposed technical addition. Is this a one-off hack, or a reusable pattern?
  • If it is generic, mandate that the solution be extracted, documented, and placed in the appropriate mind-vault/skills/ directory BEFORE it is utilized in the application.

Read the full file on GitHub · 130 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. today Changed d7d339324b81
  2. 4d ago First seen · 130 lines · 248 tokens per session scan A 312158ac848b

Subscribe to this mod's changes

architect is an agent published in the GitHub repository infohata/mind-vault (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 248 tokens to every session and 3,531 once invoked, about $0.0012 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.