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.
npx agentmods add skills/int2t05/engineering-skills/codebase-designnpx skills add int2t05/engineering-skills --skill codebase-designgit clone --depth 1 https://github.com/int2t05/engineering-skillsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00113 | $0.01681 |
| Opus 5 | $0.00056 | $0.00840 |
| Sonnet 5 | $0.00023 | $0.00336 |
| Haiku 4.5 | $0.00011 | $0.00168 |
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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Design
Design deep modules: a lot of behaviour behind a small interface, placed at a clean seam, testable through that interface. Leverage for callers, locality for maintainers, testability for everyone. This skill merges the deep-module vocabulary with a scan-and-grill workflow: surface architectural friction as deepening opportunities, present them as a visual HTML report, then grill through the one the user picks.
When to use
- Designing a new module or restructuring an existing one — deciding where a seam goes, what hides behind it
- Finding refactoring or deepening opportunities across a codebase
- Making a codebase more testable or AI-navigable
- Consolidating tightly-coupled shallow modules into one deep module
- Triggers on "deep module", "seam", "refactoring opportunity", "架构改进", "模块设计", "deepening", "深化模块", "重构架构", "代码库设计"
Not for: executing the structural change once the design is settled (use refactoring); single-file clarity cleanup — naming, nesting, dead code (use simplify); greenfield system architecture (use architecture); feature-level API contracts (use api-design). This skill designs and audits; it does not edit code.
Steps
1. Scan for deepening opportunities
Read the project's domain glossary (CONTEXT.md) and any ADRs in the area you're touching first —
the domain language names good seams; ADRs record decisions not to re-litigate.
Scope before you scan — put weight on parts of the codebase that have recently changed. If the user
named a direction, take it. Otherwise walk the commit history (git log --oneline) to find hot
spots, then explore those paths first.
Spawn an Explore sub-agent to walk the codebase and note friction (if sub-agents are unavailable in this environment, walk it yourself with Glob/Grep/Read, focusing on recently-changed files via git log --oneline -20). Note where understanding one
concept requires bouncing between many small modules; where modules are shallow (interface
nearly as complex as the implementation); where pure functions were extracted just for testability
but bugs hide in how they're called; where tightly-coupled modules leak across seams; where code
is untested or hard to test through its current interface.
What ships with it
6 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.
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.
- 2d ago First seen · 106 lines · 113 tokens per session scan A bbfba67e7e0e
codebase-design is a skill published in the GitHub repository int2t05/engineering-skills (3 stars, last pushed 13d ago), licensed MIT. It adds 113 tokens to every session and 1,681 once invoked, about $0.0006 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.
Other skills, from other repositories
absolute-work
End-to-end, phase-gated SDLC for AI coding agents: relentless design interview → reviewed spec → dependency-graphed task board → safe-wave TDD execution → verification → converge. Handles features, bugs, refactors, greenfield projects, planning breakdowns, and migrations. Triggers on "absolute work", "build this…
production-engineering-workflows
End-to-end production engineering workflows that encode the complete software development lifecycle into repeatable, quality-gated agent commands. Covers everything from spec-driven ideation through planning, test-driven implementation, automated testing, rigorous code review, web performance auditing, code…
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
nunit-testing
Use when writing or modifying tests in NUnit's own test projects, or when making a behavioral change to production code that needs test coverage. Covers test structure, attribute choice, helper visibility, platform guards, and which test projects are real.
software-test-execution
Run scoped tests for a TDD slice, determine the appropriate test framework and command, and report structured pass/fail results. Use when tests need to be executed after writing, implementing, or refactoring code. Reads test metadata, discovers the test framework if needed, executes the scoped test command, parses…
nunit-api-design
Use when adding or modifying public API surface in NUnit — new or changed constraints, attributes, assertions, helpers, or any type/member visibility change. Covers the conventions NUnit maintainers enforce for types that ship to consumers of the framework.