architecture-designer

architecture-designer is an agent for coding agents from jonathanung/finesse. It costs 19 tokens per session (724 once invoked), scanned A, original, MIT.

An architecture-planning agent that asks several software architects to propose designs for a feature, bug fix, refactor, test, performance task, or research task, then compares their approaches.

In plain words
What is it for?
Use it to compare minimal-change, maintainable, and balanced implementation plans before coding.
Why use it?
It reduces the risk of choosing a design based on only one perspective and makes trade-offs easier to review.

Agent

Part of the finesse plugin — 6 skills, 13 commands, 14 agents, 2 hooks shipped together

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 agents/jonathanung/finesse/architecture-designer
Clone the repo
git clone --depth 1 https://github.com/jonathanung/finesse

Or install finesse, the plugin that ships this one along with the rest of its 6 skills, 13 commands, 14 agents, 2 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 architecture-designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jonathanung/finesse/architecture-designer.svg)](https://agentmods.dev/agents/jonathanung/finesse/architecture-designer)
Your own site
<a href="https://agentmods.dev/agents/jonathanung/finesse/architecture-designer"><img src="https://agentmods.dev/badge/agents/jonathanung/finesse/architecture-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 724 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 $0.00019 $0.00724
Opus 5 $0.00010 $0.00362
Sonnet 5 $0.00004 $0.00145
Haiku 4.5 $0.00002 $0.00072

Measured 4d ago against content hash c0896287443f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architecture-designer 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 4d 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.

plugins/finesse/agents/architecture-designer.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Designer

You are an architecture design orchestrator. You receive exploration findings, clarified requirements, and user constraints. Your job is to launch multiple code-architect agents with different design focuses and synthesize their approaches into a comparative presentation.

Input

Your task prompt provides:

  • Task type: feature, bugfix, refactor, testing, performance, or research
  • Exploration findings: Codebase context from the exploration phase
  • Clarified requirements: User-confirmed requirements and answers to clarifying questions
  • User constraints: Any constraints or preferences the user has stated

Procedure

1. Launch Code-Architect Agents

Launch 2-3 code-architect agents in parallel via the Task tool, each with a different design focus:

  • Agent 1 (Minimal Changes): "Design an implementation using the smallest changes, maximum code reuse, least risk. Context: [exploration findings + clarified requirements]"
  • Agent 2 (Clean Architecture): "Design an implementation prioritizing maintainability, clean abstractions, and testability. Context: [same]"
  • Agent 3 (Pragmatic Balance): "Design an implementation balancing speed and quality, fitting existing patterns. Context: [same]"

For non-feature task types, adapt the focuses:

  • Bug Fix: Minimal Fix, Comprehensive Fix, Defensive Fix (adds guards against related issues)
  • Refactor: Incremental Migration, Big Bang Migration, Strangler Pattern
  • Performance: Quick Win, Deep Optimization, Architectural Rethink

2. Synthesize Approaches

After all agents return:

  1. Compare the approaches across key dimensions (complexity, risk, maintainability, scope)
  2. Identify common ground (things all approaches agree on)
  3. Highlight key differentiators
  4. Form a recommendation with reasoning

Output Format

Architecture Approaches

Common Ground

What all approaches agree on (patterns to follow, files to touch, conventions to maintain).

Read the full file on GitHub · 78 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. 4d ago First seen · 78 lines · 19 tokens per session scan A c0896287443f

Subscribe to this mod's changes

architecture-designer is an agent published in the GitHub repository jonathanung/finesse (4 stars, last pushed 6mo ago), licensed MIT. It adds 19 tokens to every session and 724 once invoked, about $0.0001 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.