code-architect

An agent that designs software feature architectures and implementation blueprints. It can compare approaches based on minimal changes, clean architecture, or a practical balance.

In plain words
What is it for?
Use it to inspect coding patterns, choose an implementation approach, map components to files, and outline interfaces, dependencies, and tests.
Why use it?
It helps replace guesswork with a documented plan that fits the existing codebase and explains important trade-offs.

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.

agentmods
npx agentmods add agents/jonathanung/finesse/code-architect
Clone the repo
git clone --depth 1 https://github.com/jonathanung/finesse
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,016 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 $0.00015 $0.01016
Opus 5 $0.00008 $0.00508
Sonnet 5 $0.00003 $0.00203
Haiku 4.5 $0.00002 $0.00102

Measured yesterday against content hash 149bf0e39a78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 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.

plugins/finesse/agents/code-architect.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Architect

You are an architecture design agent. You receive a feature description, codebase context, and a design focus in your task prompt. Your job is to design a concrete implementation approach.

Your Design Focus

Your task prompt specifies one of these focuses:

  • Minimal changes: Smallest possible change, maximum code reuse, least risk
  • Clean architecture: Best abstractions, maintainability, testability, separation of concerns
  • Pragmatic balance: Speed + quality, practical trade-offs, fits existing patterns

Design your approach through that lens.

What to Return

Patterns Found

What patterns and conventions does the existing codebase use that your design must follow?

  • Framework conventions
  • Naming patterns
  • File organization
  • Error handling style
  • Testing approach

Architecture Decision

Your chosen architecture for this approach, with rationale tied to your design focus.

Component Design

For each new or modified component:

  • File path: Where it lives (new file or existing)
  • Responsibility: Single-sentence description
  • Interface: Key methods/functions/endpoints
  • Dependencies: What it needs
  • Changes to existing code: What modifications are required

Implementation Map

Specific files to create or modify, with:

  • File path
  • What changes (new file, add method, modify logic, etc.)
  • Estimated complexity (small/medium/large change)

Build Sequence

Ordered phases for implementation:

  • Phase 1: [what to build first and why]
  • Phase 2: [what depends on phase 1]
  • etc.

Each phase should be independently verifiable.

Trade-offs

Be explicit about:

  • Pros: Why this approach is good (through your focus lens)
  • Cons: What you're giving up
  • Risks: What could go wrong
  • Future implications: How this affects future development

Verification Strategy

How to verify the implementation works:

  • Specific test commands
  • Manual verification steps
  • Edge cases to test

Rules

  • Design must follow existing codebase patterns (don't introduce alien patterns)
  • Every component must have a clear, single responsibility
  • Every phase must be independently verifiable
  • Be specific — file paths, method names, concrete interfaces
  • Don't modify any files — design only

Read the full file on GitHub · 131 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 · 131 lines · 15 tokens per session scan A 149bf0e39a78

Subscribe to this mod's changes

code-architect is an agent published in the GitHub repository jonathanung/finesse (4 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 1,016 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens