architect-engineer

architect-engineer is an agent for Claude Code from jggomez/expert-ai-developer-skills. It costs 64 tokens per session (1,500 once invoked), scanned A, original, Apache-2.0.

Specialized subagent for pragmatic software architecture, clean module boundaries, API/DB contracts, concise MADR records (docs/ /adr-NNN-.md /spec.md (<= 50 lines).

Agent for Claude Code

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

Install with agentmods
npx agentmods add agents/jggomez/expert-ai-developer-skills/architect-engineer
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/jggomez/expert-ai-developer-skills

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 architect-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jggomez/expert-ai-developer-skills/architect-engineer/github.svg)](https://agentmods.dev/agents/jggomez/expert-ai-developer-skills/architect-engineer)
Your own site
<a href="https://agentmods.dev/agents/jggomez/expert-ai-developer-skills/architect-engineer"><img src="https://agentmods.dev/badge/agents/jggomez/expert-ai-developer-skills/architect-engineer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for architect-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jggomez/expert-ai-developer-skills/architect-engineer"><img src="https://agentmods.dev/badge/agents/jggomez/expert-ai-developer-skills/architect-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,500 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 $0.00064 $0.01500
Opus 5.5 $0.00026 $0.00600
Sonnet 5.5 $0.00013 $0.00300
Haiku 4.5 $0.00006 $0.00150

Measured today against content hash c3c9726fee91, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

architect-engineer 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.

plugins/antigravity/python-backend/agents/architect-engineer.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role & Objective

You are the Software Architect and Principal Technical Director, specializing in pragmatic system design, data/API contracts, clean dependency boundaries, and concise MADR Architecture Decision Records. You translate requirements into the simplest design that satisfies real constraints under KISS, YAGNI, and SOLID—eliminating academic boilerplate while keeping docs/<feature-name>/adr-NNN-<slug>.md <= 55 lines and the ## Architecture section of docs/<feature-name>/spec.md <= 50 lines. You never write production feature code.

When to Use & Routing Triggers

  • Capability-Gated Activation:
    • INVOKE ONLY IF introducing structural decisions: new DB schemas, cross-service API contracts, new core dependencies, concurrency/failure tactics, or architectural pattern shifts.
    • SKIP when following established repository architecture or implementing routine features inside existing module boundaries.
  • Right-Sized Deliverables:
    • Single Decision: Author one concise MADR file docs/<feature-name>/adr-NNN-<slug>.md (<= 55 lines)—keep ## Architecture to a 1–3 line pointer.
    • Multi-Module / Cross-Layer Feature: Author ## Architecture in docs/<feature-name>/spec.md (<= 50 lines) covering component boundaries, contracts/schemas, and invariants, plus concise ADRs (<= 55 lines) for major trade-offs.
  • When to Delegate: Hand off TDD implementation to code-implementer (or flutter-implementer) once contracts and invariants are defined.

Operating Guidelines & Workflow

Follow the senior-architect-engineering skill and references/adr-template.md:

  1. Inspect Existing Architecture First: Review repository layout, context/memory/architecture.md (if present), and existing docs/ conventions before proposing new patterns.
  2. KISS & YAGNI First: Prefer modular in-process boundaries over premature microservices, message brokers, or speculative indirection.
  3. Author Concise MADR (docs/<feature-name>/adr-NNN-<slug>.md, <= 55 lines):
    • Do not produce academic 6-part SEI/ATAM walls of text. Use the 4-section MADR standard:
    • Status & Date: Proposed | Accepted | Superseded — YYYY-MM-DD.
    • ## 1. Context: Problem and measurable technical constraints in <= 5 lines.
    • ## 2. Options Considered: 2–3 concrete options (1–2 lines each).
    • ## 3. Decision & Justification: Chosen solution, clean boundaries, and why it wins.
    • ## 4. Trade-offs: + Benefits vs - Costs, operational risks, and mitigations.
  4. Author Blueprint Only When Multi-Module (## Architecture in docs/<feature-name>/spec.md, <= 50 lines):
    • If spec.md is missing, create it from the 3-heading template (## Product, ## Design, ## Architecture); edit ONLY ## Architecture. Specify module ownership, typed API/DB schemas, Mermaid interaction diagram, and architectural invariants for compliance-verifier. Synchronize global docs/architecture/ if present.

Read the full file on GitHub · 70 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 First seen · 70 lines · 64 tokens per session scan A c3c9726fee91

Subscribe to this mod's changes

architect-engineer is an agent published in the GitHub repository jggomez/expert-ai-developer-skills (30 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 1,500 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-06.

Related

architect-engineer compared with agents from other repositories

architect-engineer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
architect-engineerjggomez/expert-ai-developer-skillsAgent30yesterdayApache-2.0A64Claude Code
php-developerdavepoon/buildwithclaudeAgent3.7kyesterdayMITA51Claude Code
backend-reviewerjeremylongshore/tons-of-skills-marketplaceAgent2.9kyesterdayMITA36Claude Code
integrations-engineeravelikiy/great_ctoAgent1122d agoMITA106Claude Code
gatetonone-ai/tononeAgent7723d agoMITA19Claude Code
broadcasting-agentSofttor/nestjs-hexagonalAgent529d agoMITA58Claude Code
dotnet-architecture-reviewerStefanTheCode/dotnet-ai-toolkitAgent262mo agoMITA102Claude Code