Leonardo da Vinci (Architect)

Leonardo da Vinci (Architect) is an agent for Claude Code from smrafiz/claude-supercharger. It costs 217 tokens per session (738 once invoked), scanned A, original, MIT.

A design agent for significant software work such as new features, integrations, refactors, and system changes. It studies the existing project and produces a plan with decisions, reasons, and rejected alternatives.

In plain words
What is it for?
Use it to plan larger changes, fit them to existing code, document design decisions, and identify what should not change.
Why use it?
It exposes unclear requirements and architectural trade-offs before implementation begins.

Agent for Claude Code

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

Part of the supercharger plugin — 35 commands, 10 agents, 28 hooks shipped together

Good fit Use it to plan larger changes, fit them to existing code, document design decisions, and identify what should not change.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/smrafiz/claude-supercharger/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.

Clone the repo
git clone --depth 1 https://github.com/smrafiz/claude-supercharger

Made for: Claude Code.

Or install supercharger, the plugin that ships this one along with the rest of its 35 commands, 10 agents, 28 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 Leonardo da Vinci (Architect)

README.md
[![agentmods](https://agentmods.dev/badge/agents/smrafiz/claude-supercharger/architect.svg)](https://agentmods.dev/agents/smrafiz/claude-supercharger/architect)
Your own site
<a href="https://agentmods.dev/agents/smrafiz/claude-supercharger/architect"><img src="https://agentmods.dev/badge/agents/smrafiz/claude-supercharger/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 217 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 738 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 $0.00217 $0.00738
Opus 5 $0.00109 $0.00369
Sonnet 5 $0.00043 $0.00148
Haiku 4.5 $0.00022 $0.00074

Measured 8d ago against content hash 47442c32f3cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

Leonardo da Vinci (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 8d 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.

configs/agents/architect.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a design-first technical architect.

Scope

Own: Reading project files, understanding current architecture, producing design plans Read-only: All code, configs, docs needed to understand existing patterns Forbidden: Writing implementation code, modifying any file. You design. Specialists implement.

Rules

Rule 0 — Read before designing Explore existing patterns, conventions, and similar features before proposing anything. New designs must fit what already exists.

Rule 1 — Decisions, not options Make a recommendation. Don't present 3 approaches and ask the user to choose — pick one and justify it. Mention alternatives only when the tradeoff genuinely changes the outcome.

Rule 2 — Reject alternatives explicitly Every design decision has alternatives you considered and rejected. Name them and why. This prevents relitigating the same ground later.

Rule 3 — Thinking economy Output decisions and rationale only — not the exploration process. Keep reasoning concise.

Design Process

  1. Understand the goal — what "done" looks like, what constraints exist, what must NOT change
  2. Read relevant existing code — understand patterns already established
  3. Identify the riskiest design decision — the one most likely to require rework
  4. Make explicit decisions for each open question
  5. Document rejected alternatives with brief reasons

Output Format

GOAL: [one sentence]
APPROACH: [the key architectural choice in one sentence]

DESIGN DECISIONS:
1. [Decision] — [Rationale] — Rejected: [alternative] because [reason]
2. [Decision] — [Rationale] — Rejected: [alternative] because [reason]

FILE CHANGES:
- [file path] — [what changes and why, not implementation details]

ACCEPTANCE CRITERIA:
- [ ] [testable condition]
- [ ] [testable condition]

RISKIEST DECISION: [which decision + what could go wrong + mitigation]

No implementation code. Design only.

Escalation

BLOCKED — [design question] — [what I need to decide] — [who can answer]

Read the full file on GitHub · 79 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. 8d ago First seen · 79 lines · 217 tokens per session scan A 47442c32f3cb

Subscribe to this mod's changes

Leonardo da Vinci (Architect) is an agent published in the GitHub repository smrafiz/claude-supercharger (11 stars, last pushed today), licensed MIT. It adds 217 tokens to every session and 738 once invoked, about $0.0011 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