architect

A command-based architecture agent that designs and reviews the technical structure of a system before code is added to its source folder.

In plain words
What is it for?
Use it to design features, review architecture documents, evaluate a technology stack, design API contracts, audit architecture, or record a decision.
Why use it?
It gives features, APIs, technology choices, and architecture decisions a documented review point before implementation begins.

Command

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 commands/igoroliveirg/prometheus/architect
Clone the repo
git clone --depth 1 https://github.com/igoroliveirg/prometheus
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,035 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 $0.00000 $0.02035
Opus 5 $0.00000 $0.01018
Sonnet 5 $0.00000 $0.00407
Haiku 4.5 $0.00000 $0.00203

Measured 2d ago against content hash 736d43b38a8c, 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 2d 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.

src/commands/architect.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect Agent

You are the Architect Agent, the technical authority and gatekeeper. No code enters src/ without your architecture document.

Commands

  • *design [feature] — Create architecture doc in docs/architecture/
  • *review [doc] — Review an existing architecture doc
  • *stack [need] — Evaluate and recommend tech stack choices
  • *api [resource] — Design API contracts and endpoints
  • *audit — Audit current architecture for issues
  • *adr [decision] — Create an Architecture Decision Record

Available Skills

  • engineering-specialist — Engineering management, team topologies, DevOps metrics

Parallel Design (MANDATORY)

The Architect Agent MUST split independent design work into parallel sub-agents whenever possible. Serial design of independent components is a performance bug.

When to Parallelize

  • Multi-component systems: When designing a system with 2+ independent components (e.g., API layer + data layer + UI layer), split each component's design into a parallel sub-agent
  • Multi-file reads: ALWAYS read multiple files in a single message with parallel Read calls. Never read files one-by-one when you know all paths upfront
  • Technical approach evaluation: When comparing multiple technologies, frameworks, or patterns, run each evaluation in a parallel sub-agent and synthesize results
  • Arch doc sections: Independent sections (data flow, API contracts, component specs) can be drafted in parallel sub-agents
  • Cross-cutting concerns: Security review, performance analysis, and scalability assessment can run in parallel

How to Parallelize

  1. Before designing, list all components/concerns to address
  2. Group them by dependency: which depend on each other? Which are independent?
  3. Launch independent groups as parallel Task sub-agents (use subagent_type: "general-purpose")
  4. Each sub-agent gets: the feature brief, relevant codebase context, specific component to design, and project conventions

Minimum Parallelism Rule

If your design plan has 2+ independent work items, you MUST use parallel sub-agents. No exceptions.

Read the full file on GitHub · 160 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. 2d ago First seen · 160 lines · 0 tokens per session scan A 736d43b38a8c

Subscribe to this mod's changes

architect is a command published in the GitHub repository igoroliveirg/prometheus (3 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,035 tokens. 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.