Skip to content
Agentmart
Submit a tool

codebase-design

Design module interfaces or evaluate module depth when reviewing architecture, coupling, or testability.

Skill by paulorsv01

IndexedMIT
Write a review

Chalk Labs

Need help deploying codebase-design?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/paulorsv01-codebase-design

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Design module interfaces or evaluate module depth when reviewing architecture, coupling, or testability.

Use cases: design

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/codebase-design

What's inside

Skill name
codebase-design
Description
Design module interfaces or evaluate module depth when reviewing architecture, coupling, or testability.
License
MIT
Instructions
32 lines in SKILL.md · view on GitHub

Files (5)

  • DEEPENING.md
  • DESIGN-IT-TWICE.md
  • SKILL.md
  • openai.yaml · agents/
  • skill.toml

SKILL.md (first lines)

# Codebase Design

Design deep modules: substantial behavior behind an interface callers can understand with little effort.
Preserve the project's domain vocabulary. Use the terms below for architectural reasoning.

## Vocabulary

- **Module**: a function, class, package, or larger slice with an interface and implementation.
- **Interface**: everything callers need to know, including types, invariants, ordering, errors, configuration, and performance guarantees.
- **Implementation**: the behavior hidden behind the interface.
- **Seam**: a place where behavior can vary without editing its callers. An **adapter** satisfies the interface at that seam.
- **Depth**: useful behavior per amount callers must learn. It gives callers **leverage** and concentrates change in one place, improving **locality**.

## Decision criteria

Judge depth by caller complexity, not implementation line counts.
A useful module hides decisions that would otherwise spread across callers.
Reduce exposed methods, parameters, and ordering constraints when that makes real callers simpler.
Justify new seams with actual variation, such as production and test adapters.
Internal seams can support implementation tests without becoming part of the public interface.

## Focused references

For a cluster with coupled dependencies, read [DEEPENING.md](DEEPENING.md).
For comparison of alternative interfaces, read [DESIGN-IT-TWICE.md](DESIGN-IT-TWICE.md).

## Completion

For a design request, present the interface, caller example, hidden responsibilities, and relevant trade-offs.
For an implementation request, integrate the chosen interface and verify affected behavior through a meaningful interface.

From paulorsv01/agents, MIT.

More from paulorsv01/agents

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 24, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from paulorsv01

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get codebase-design running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying codebase-design?

CallGet help
Cite this page

codebase-design skill. Agent Mart. https://agentmart.dev/skills/paulorsv01-codebase-design (last updated 2026-10-24)