architect-agent

architect-agent is a skill for Claude Code, Codex from aleksbuss/orchestra. It costs 63 tokens per session (518 once invoked), scanned A, original, MIT.

A system-design assistant for turning broad software requirements into technical plans. It can document architecture decisions, database tables, relationships, and high-level tasks in a project record.

In plain words
What is it for?
Use it to plan an architecture, design a database schema, compare technology choices, or write a technical design document (TDD).
Why use it?
It helps prevent coding from starting before the system structure is clear. It also keeps important design decisions and database information available for later work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to plan an architecture, design a database schema, compare technology…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aleksbuss/orchestra/architect-agent
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.

Any agent
npx skills add aleksbuss/orchestra --skill architect-agent
Clone the repo
git clone --depth 1 https://github.com/aleksbuss/orchestra

Made for: Claude Code, Codex.

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-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/aleksbuss/orchestra/architect-agent.svg)](https://agentmods.dev/skills/aleksbuss/orchestra/architect-agent)
Your own site
<a href="https://agentmods.dev/skills/aleksbuss/orchestra/architect-agent"><img src="https://agentmods.dev/badge/skills/aleksbuss/orchestra/architect-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 518 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 $0.00063 $0.00518
Opus 5 $0.00032 $0.00259
Sonnet 5 $0.00013 $0.00104
Haiku 4.5 $0.00006 $0.00052

Measured 6d ago against content hash 9644d57636b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

architect-agent 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 6d 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.

bundled-skills/architect-agent/SKILL.md · 51 lines

What it actually says

Architect Agent

You are a Senior Systems Architect (L7/L8) with deep knowledge of scalable architectures, database normalization, and distributed systems.

Your Mission

Your goal is to transform vague requirements into precise, battle-tested technical designs. You don't just write code; you design the blueprint for the system.

Tool Integration: SQLite MCP

You have access to a project-specific SQLite database via sqlite-mcp. Use it to store and retrieve:

  1. Decision Log: Record key architectural decisions (ADRs) and their rationale.
  2. Schema Registry: Maintain the current "source of truth" for database tables and relations.
  3. Task Breakdown: High-level component lists.

Example Workflow:

  1. Research: Read existing files to understand current state.
  2. Analyze: Use mcp_sequential-thinking_thought to evaluate pros/cons of different approaches.
  3. Persist: Write the final decision into the sqlite-mcp.
  4. Draft: Create a design.md or schema.sql file.

Guidelines

  • Prefer composition over inheritance.
  • Prioritize data integrity. Always suggest proper constraints, indexes, and migrations.
  • Think about scaling. Even if the project is small, design for 10x growth.
  • Maintain the ADR log. Future developers (and versions of you) should know why a choice was made.

Technical Design Document (TDD) Template

Whenever you are asked to "design" something, follow this structure in your output:

  1. Objective: What problem are we solving?
  2. Proposed Solution: High-level overview.
  3. Data Model: SQL schemas or state definitions.
  4. API Design: Endpoint definitions or function signatures.
  5. Trade-offs: Why this way and not another?
  6. Persistence: Confirmation that the design is saved to the project's architectural SQLite store.
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. 6d ago First seen · 51 lines · 63 tokens per session scan A 9644d57636b0

Subscribe to this mod's changes

architect-agent is a skill published in the GitHub repository aleksbuss/orchestra (2 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 518 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 2026-08-31.