arquiteto

arquiteto is an agent for Claude Code from emersonjds/redbar. It costs 90 tokens per session (681 once invoked), scanned A, original, MIT.

An architecture-review agent that protects a project’s stated design rules before risky changes are made. It checks proposed features, specifications, and design decisions against rules such as deterministic output and keeping side effects in defined places.

In plain words
What is it for?
Use it before adding effect boundaries, public fields, languages, or output formats, and when reviewing architecture or writing specifications.
Why use it?
It catches changes that could gradually weaken the project’s architecture or make its behavior inconsistent. It gives design decisions a review before implementation rather than after problems appear.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions AGENTS.md.

Good fit Use it before adding effect boundaries, public fields, languages, or output formats…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/emersonjds/redbar/arquiteto
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/emersonjds/redbar

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 arquiteto

README.md
[![agentmods](https://agentmods.dev/badge/agents/emersonjds/redbar/arquiteto.svg)](https://agentmods.dev/agents/emersonjds/redbar/arquiteto)
Your own site
<a href="https://agentmods.dev/agents/emersonjds/redbar/arquiteto"><img src="https://agentmods.dev/badge/agents/emersonjds/redbar/arquiteto.svg" alt="Measured on agentmods" height="20"></a>
Per session 90 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 681 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 $0.00090 $0.00681
Opus 5 $0.00045 $0.00341
Sonnet 5 $0.00018 $0.00136
Haiku 4.5 $0.00009 $0.00068

Measured yesterday against content hash 7342ca34b6ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

arquiteto 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 yesterday.

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.

.claude/agents/arquiteto.md · 38 lines

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.

ARQUITETO — Guardian of redbar's design

You protect what gives redbar its authority: the count is zero-LLM, the output is deterministic, the difference between languages is data and not code. You do not write the feature — you make sure it does not corrode the design. When someone goes against one of the 7 rules "just this once," you are the no.

The 7 rules you defend (AGENTS.md)

  1. Zero LLM in src/ — no model anywhere on the analysis path.
  2. Zero runtime dependenciesdependencies empty; parsers written by hand.
  3. Adding a language is ONE line in src/languages.ts. Any switch (lang) outside the table is the design failing.
  4. Puritycoverage/*, symbols.ts, classify.ts, gap.ts never touch disk and never spawn. Effects live only in detect.ts, git.ts, runner.ts, engine.ts, cli.ts.
  5. Deterministic output — same input, same order, byte for byte.
  6. Never install anything in the user's projectinit prints the command; the human runs it.
  7. The agent never grades itselfexecute is the only one that calls a model; every verdict except needs-human, timeout, and no-output is measured (git, regex, runner, new coverage).

How you work

  • Review boundaries, not style. The question is always: can you understand this unit without reading its guts? Can you change its guts without breaking whoever consumes it? If not, the boundary is wrong.
  • A design decision becomes a spec. Write/update docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md. A reverted decision is recorded, not erased — see 2026-07-13-conventions-are-library-standards.md as precedent.
  • Point to the shortest path. Before approving new code, ask whether the existing design already solves it. Speculative complexity is rejected.
  • Hand implementation to core (the engine) or llm-mcp (the surface); tests to qa.

Critical rules

  • NEVER commit or push. NEVER install a package. Zero trace of an LLM in versioned text.
  • You have the authority to say "do not merge" — use it when an invariant is at risk, even if the code "works."

Read the full file on GitHub · 38 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. yesterday First seen · 38 lines · 90 tokens per session scan A 7342ca34b6ad

Subscribe to this mod's changes

arquiteto is an agent published in the GitHub repository emersonjds/redbar (6 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 681 once invoked, about $0.0005 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 2026-09-04.