codebase-design

A design guide for improving the boundaries between parts of a codebase. It focuses on keeping useful behavior behind small, stable interfaces, where an interface is the knowledge callers need to use a module.

In plain words
What is it for?
Use it to choose module boundaries, create seams where behavior can vary, improve testability and code navigation, and compare alternative designs.
Why use it?
It helps reduce the amount callers must understand and limits how far a change spreads through the code.

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/stevesolun/ctx/codebase-design
Any agent
npx skills add stevesolun/ctx --skill codebase-design
Clone the repo
git clone --depth 1 https://github.com/stevesolun/ctx

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 525 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 $0.00040 $0.00525
Opus 5 $0.00020 $0.00262
Sonnet 5 $0.00008 $0.00105
Haiku 4.5 $0.00004 $0.00052

Measured 2d ago against content hash f8bdd1b33e97, 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 2d 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.

.agents/skills/codebase-design/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Design

Seek deep modules: substantial useful behavior behind a small, stable interface. Use the concepts below as design lenses, while matching the repository's established domain language.

Working vocabulary

  • Module: a coherent unit with an interface and implementation, at any scale.
  • Interface: everything callers must know, including invariants and failure modes—not just a type signature.
  • Seam: a location where behavior can vary without editing its callers.
  • Adapter: an implementation that connects at a seam.
  • Depth: useful capability relative to interface complexity.
  • Leverage: capability gained by callers; locality: change and knowledge concentrated for maintainers.

Translate these terms to the project's vocabulary when that makes the design clearer. Consistency with the codebase is more valuable than enforcing a private lexicon.

Design workflow

  1. Map representative callers, responsibilities, dependencies, and existing contracts.
  2. Look for coordination or policy that can move behind a smaller interface.
  3. Place seams where variation, ownership, or test isolation justifies them.
  4. Compare alternatives when the choice is consequential.
  5. Validate the candidate with representative caller code and tests.

Heuristics, not laws

  • Reduce methods, parameters, ordering constraints, and configuration callers must understand.
  • Use the deletion test: if removing a module merely spreads its complexity across callers, it was likely earning its keep.
  • Treat pass-through layers skeptically, but keep them when they provide a real compatibility, ownership, policy, or navigation boundary.
  • Introduce dependency seams when actual variation or test isolation repays the indirection; avoid interfaces justified only by hypothetical futures.
  • Prefer tests through observable interfaces, while allowing focused internal tests when they provide cheaper or more precise feedback.
  • Favor explicit dependencies and returned results when they improve control and testability; side effects and internally created dependencies can still be appropriate at well-defined boundaries.

Read the full file on GitHub · 55 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 55 lines · 40 tokens per session scan A f8bdd1b33e97

Subscribe to this mod's changes

codebase-design is a skill published in the GitHub repository stevesolun/ctx (581 stars, last pushed 8d ago), licensed MIT. It adds 40 tokens to every session and 525 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 2026-08-30.

Related

Other skills, from other repositories

agent-code-analyzer

Agent skill for code-analyzer - invoke with $agent-code-analyzer.

ruvnet/ruflo · 19 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

haiku

When writing a haiku for this bot, follow these conventions.

agno-agi/agno · 0 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens