codebase-design

codebase-design is a skill for Claude Code, Codex from znlgis/my-opencode-deepseek-config. It costs 42 tokens per session (517 once invoked), scanned A, original, MIT.

A vocabulary for discussing code structure, including modules, interfaces, boundaries, adapters, and places where behavior can be changed or tested. It is a glossary for design discussions, not a step-by-step process.

In plain words
What is it for?
Use it when designing module boundaries, defining interfaces, reviewing code structure, finding test seams, or deciding whether an adapter is worthwhile.
Why use it?
It gives a team precise words for reviewing architecture and avoids mixing terms such as component, service, API, and interface when they mean different things.

Skill for Claude CodeCodex

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 skills/znlgis/my-opencode-deepseek-config/codebase-design
Any agent
npx skills add znlgis/my-opencode-deepseek-config --skill codebase-design
Clone the repo
git clone --depth 1 https://github.com/znlgis/my-opencode-deepseek-config

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 codebase-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/codebase-design.svg)](https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/codebase-design)
Your own site
<a href="https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/codebase-design"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/codebase-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 517 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 $0.00042 $0.00517
Opus 5 $0.00021 $0.00259
Sonnet 5 $0.00008 $0.00103
Haiku 4.5 $0.00004 $0.00052

Measured yesterday against content hash 5fcc283f94ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-design 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.

opencode/skills/codebase-design/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Design

A shared vocabulary for reasoning about code structure. This is a glossary, not a process — use the terms precisely so design discussions stay concrete. Adopt these words over looser ones: say module, not component or service; say interface, not API.

Terms

  • Module — a unit of code with a boundary and a purpose. Not "component" or "service"; those imply a specific framework or deployment shape.
  • Interface — everything a caller must know to use a module correctly: its functions, its invariants, its error modes, and its performance characteristics. Wider than "API" — it includes the contract a caller relies on.
  • Depth — the leverage a module gives per unit of interface. A deep module hides a lot of implementation behind a small interface. A shallow module has a large interface relative to the work it does.
  • Seam — a place where you can alter behavior without editing that place (Feathers). A seam is where you insert a test double or swap an implementation.
  • Adapter — code that translates one interface to another. One adapter is a hypothetical seam; two adapters make it a real seam worth keeping.
  • Leverage — how much downstream code a module's design decision affects. High-leverage decisions (a widely-imported module's interface) deserve the most design care.
  • Locality — whether related code lives close together. Poor locality forces readers to jump across the codebase to understand one behavior.

Tests

  • Deletion test — delete a module. Does its complexity vanish, or does it reappear scattered across N callers? If the latter, the module was not encapsulating anything real.
  • Depth test — is the interface smaller than the implementation it hides? A module whose interface is as big as its body is shallow and probably not earning its place.

Testability

  • Accept dependencies; do not create them inside the module.
  • Return results; do not produce side effects from a function that claims to compute.
  • Keep the surface small — every public entry point is a promise you maintain.

Read the full file on GitHub · 48 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 · 48 lines · 42 tokens per session scan A 5fcc283f94ed

Subscribe to this mod's changes

codebase-design is a skill published in the GitHub repository znlgis/my-opencode-deepseek-config (57 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 517 once invoked, about $0.0002 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 2026-09-03.