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/astordu/qoderharness/codebase-designnpx skills add astordu/qoderharness --skill codebase-designgit clone --depth 1 https://github.com/astordu/qoderharnessWhat 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 | $0.00074 | $0.01797 |
| Opus 5 | $0.00037 | $0.00898 |
| Sonnet 5 | $0.00015 | $0.00359 |
| Haiku 4.5 | $0.00007 | $0.00180 |
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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
代码库设计(Codebase Design)
设计深模块(deep module):在小接口背后承载大量行为,置于一个清晰的接缝处,并可通过该接口进行测试。无论在何处设计或重构代码,都使用这套语言和这些原则。目标是:为调用方带来杠杆(leverage),为维护者带来局部性(locality),为所有人带来可测试性(testability)。
术语表
请精确使用这些术语——不要用「组件(component)」「服务(service)」「API」或「边界(boundary)」来替代。语言的一致性正是全部要点所在。
模块(Module) —— 任何具有接口和实现的东西。刻意做到与规模无关:可以是一个函数、类、包,或跨层的一段切片。避免:单元(unit)、组件(component)、服务(service)。
接口(Interface) —— 调用方为正确使用该模块所必须了解的一切:类型签名,以及不变量、顺序约束、错误模式、必需的配置和性能特征。避免:API、签名(signature)(太狭窄——它们只指类型层面的表层)。
实现(Implementation) —— 模块内部的东西,它的代码主体。与**适配器(Adapter)**有别:一个东西可以是「小适配器 + 大实现」(如 Postgres 仓储),也可以是「大适配器 + 小实现」(如内存伪实现)。当接缝是讨论主题时,用「适配器」;否则用「实现」。
深度(Depth) —— 接口处的杠杆:调用方(或测试)每学习一个单位的接口,能够驱动多少行为。当大量行为藏在小接口背后时,模块是**深(deep)的;当接口几乎与实现一样复杂时,模块是浅(shallow)**的。
接缝(Seam) (Michael Feathers) —— 一个你无需在此处编辑就能改变行为的位置;模块接口所在的地点。接缝放在哪里本身就是一项独立的设计决策,与接缝背后放什么有别。避免:边界(boundary)(因与 DDD 的限界上下文含义重叠而被过度使用)。
适配器(Adapter) —— 在某个接缝处满足接口的具体事物。它描述的是角色(填补哪个槽位),而非实质(内部是什么)。
杠杆(Leverage) —— 调用方从深度中获得的东西:每学习一个单位的接口就获得更多能力。一份实现可在 N 个调用点和 M 个测试中反复收益。
局部性(Locality) —— 维护者从深度中获得的东西:变更、缺陷、知识和验证都集中在一处,而非散落到各个调用方。修一次,处处皆修。
深 vs 浅
深模块 = 小接口 + 大量实现:
┌─────────────────────┐
│ Small Interface │ ← Few methods, simple params
├─────────────────────┤
│ │
│ Deep Implementation│ ← Complex logic hidden
│ │
└─────────────────────┘
浅模块 = 大接口 + 少量实现(应避免):
┌─────────────────────────────────┐
│ Large Interface │ ← Many methods, complex params
├─────────────────────────────────┤
│ Thin Implementation │ ← Just passes through
└─────────────────────────────────┘
设计接口时,问自己:
- 我能减少方法的数量吗?
- 我能简化参数吗?
- 我能把更多复杂性藏进内部吗?
原则
- 深度是接口的属性,而非实现的属性。 一个深模块的内部可以由许多小的、可 mock、可替换的部件组成——它们只是不属于接口的一部分。模块既可以拥有内部接缝(internal seam)(对其实现私有,供自身测试使用),也可以在其接口处拥有外部接缝(external seam)。
- 删除测试(deletion test)。 设想删掉这个模块。如果复杂性随之消失,那它只是一个透传(pass-through)。如果复杂性在 N 个调用方处重新冒出来,那它就是在发挥价值。
- 接口即测试面(test surface)。 调用方和测试跨越的是同一个接缝。如果你想测试接口之外/之内的东西,那这个模块的形状很可能不对。
- 一个适配器意味着假想的接缝;两个适配器意味着真实的接缝。 除非确实有东西在接缝两侧发生变化,否则不要引入接缝。
What ships with it
2 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 · 115 lines · 74 tokens per session scan A db1de28d573c
codebase-design is a skill published in the GitHub repository astordu/qoderharness (21 stars, last pushed 6d ago), licensed MIT. It adds 74 tokens to every session and 1,797 once invoked, about $0.0004 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.
Other skills, from other repositories
planning-with-files-ar
تخطيط مستمر قائم على الملفات لعمل وكلاء الذكاء الاصطناعي متعدد الخطوات. يحتفظ بملفات taskplan.md و findings.md و progress.md على القرص، وتحقن خطافات دورة الحياة سياق التخطيط المحدد للمشروع. تقرأ الاستعادة التلقائية ملفات تخطيط المشروع فقط. يمكن للأمر الصريح session-catchup.py --metadata فحص بيانات وصفية لجلسات الوكيل…
kl-consistency-test
Write, calibrate, and debug the prefill-vs-decode logprob (KL) consistency tests in sglang -- the two independent conditions a zero requires (every operator batch-invariant, and the two paths computing the same function), which helper separates them, how to pick a threshold once they hold, and how to localize a…
i18n-localization
Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.
dsh-web-documentation
Use when adding or editing dsh-web README files, docs, AGENTS.md instructions, user-facing configuration text, or bilingual documentation pairs.
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
indication-dossier
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.