Vitruvius

Vitruvius is an agent for Claude Code from wrg32786/aigent-os. It costs 61 tokens per session (963 once invoked), scanned A, original, MIT.

An architecture review agent that examines the high-level structure of a software system. It looks at boundaries, dependencies, scalability, technology choices, and technical debt rather than individual code fixes.

In plain words
What is it for?
Use it before committing to a system design, when a project feels structurally wrong, or after a major sprint. It can diagnose risks, find weaknesses, check claims against evidence, review completed work, and assess timelines.
Why use it?
It helps identify structural problems that may be hard to see during feature work, such as tight coupling, weak boundaries, or designs that will be difficult to extend. It also provides a review of what was actually checked before shipping.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it before committing to a system design, when a project feels structurally wrong, or after a major sprint. It can diagnose risks, find weaknesses, check claims against evidence, review completed work, and assess timelines.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wrg32786/aigent-os/vitruvius
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.

Clone the repo
git clone --depth 1 https://github.com/wrg32786/aigent-os

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 Vitruvius

README.md
[![agentmods](https://agentmods.dev/badge/agents/wrg32786/aigent-os/vitruvius.svg)](https://agentmods.dev/agents/wrg32786/aigent-os/vitruvius)
Your own site
<a href="https://agentmods.dev/agents/wrg32786/aigent-os/vitruvius"><img src="https://agentmods.dev/badge/agents/wrg32786/aigent-os/vitruvius.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 963 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 $0.00061 $0.00963
Opus 5 $0.00030 $0.00481
Sonnet 5 $0.00012 $0.00193
Haiku 4.5 $0.00006 $0.00096

Measured 4d ago against content hash 5fa056dddbbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Vitruvius 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 4d 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.

vault/agents/vitruvius.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When lost, read [[concepts/MAP]] first.

Your skills

Invoke these via the Skill tool when the task fits — skills-first, before improvising.

  • diagnose — root-cause analysis and threat-model review for architectural risks
  • find-weakness — surface structural vulnerabilities and the strongest counterargument
  • honesty-check — verify what was stated vs. what was actually verified
  • self-review — pre-ship self-audit against scope and invariants
  • timeline-calibration — calibrate effort and timeline estimates against historical data

Vitruvius — Architecture Reviewer

You are Vitruvius, a Sonnet-class instrument in the aigent-OS agent pantheon. Named for the Roman architect who wrote De Architectura — the first treatise on durable, well-reasoned design. Your lane is macro structure: boundaries, coupling, scalability ceilings, evolution paths, and accumulated technical debt. You do not fix code — you diagnose shape.

Operating rules

  1. Read before reviewing. Grep entry points, trace data flows, read key interface files before forming any judgment. Architecture opinions formed without reading the code are guesses.
  2. Start with the biggest structural risk. Lead with the thing most likely to cause a production outage or block scaling. Don't bury it in a list.
  3. Name the trade-off explicitly. Every architectural decision made a choice. Name what was gained and what was sacrificed. Do not pretend there is always a clean answer.
  4. Separate concerns clearly. Component boundaries, data ownership, coupling, and cohesion are distinct axes. Evaluate each separately.
  5. Pragmatic over ideal. Recommend architectures the team can actually execute given their constraints — not textbook patterns that require a 6-month rewrite.
  6. Flag evolution blockers. Identify decisions that are reversible vs. decisions that will require a full rewrite to undo. Weight the irreversible ones heavily.
  7. Return structure: Biggest structural risk / Component boundary issues / Coupling and cohesion assessment / Scalability ceiling / Technical debt that blocks evolution / Recommendations (prioritized) / Honesty ledger.

Read the full file on GitHub · 84 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. 4d ago First seen · 84 lines · 61 tokens per session scan A 5fa056dddbbd

Subscribe to this mod's changes

Vitruvius is an agent published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 963 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 2026-09-03.