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/improve-codebase-architecturenpx skills add astordu/qoderharness --skill improve-codebase-architecturegit 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 | $0.00056 | $0.01755 |
| Opus 5 | $0.00028 | $0.00877 |
| Sonnet 5 | $0.00011 | $0.00351 |
| Haiku 4.5 | $0.00006 | $0.00176 |
Grade A, and why
improve-codebase-architecture 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
改进代码库架构(Improve Codebase Architecture)
暴露架构上的摩擦,并提出 加深机会(deepening opportunities)——把浅模块变为深模块的重构。目标是可测试性与对 AI 友好的可导航性。
这条命令 受 项目领域模型 启发,并构建在一套共享的设计词汇之上:
- 运行
/codebase-design技能,获取架构词汇(module 模块、interface 接口、depth 深度、seam 接缝、adapter 适配器、leverage 杠杆、locality 局部性)及其原则(删除测试、"接口即测试面"、"一个适配器 = 假想的接缝,两个 = 真实的接缝")。在每一条建议中都精确地使用这些术语——不要漂移成 "component"、"service"、"API" 或 "boundary"。 CONTEXT.md中的领域语言为好的接缝命名;docs/adr/中的 ADR 记录了这条命令不应重新翻案的决策。
流程
1. 探索
在扫描之前先划定范围——YAGNI。 加深一个模块的回报,来自让它未来更易于改动,所以要对代码库中近期变动过的部分格外看重。在动手看之前先决定 看哪里:
- 如果用户指明了方向——某个模块、某个子系统、某个痛点——就采纳它,并跳过下面的推断。
- 否则,回溯一段相当长的提交历史(
git log --oneline),找出代码库的热点——那些反复出现的文件和区域——让这些路径优先吸引你的注意。如果改动分散、没有明显热点,就把网撒得更宽一些。
先阅读项目的领域词汇表(CONTEXT.md)以及你所触及区域内的所有 ADR。
然后用 Agent 工具(subagent_type=Search)来遍历代码库。不要遵循僵化的启发式规则——有机地探索,并记下你感到摩擦的地方:
- 哪里为了理解一个概念,需要在许多小模块之间来回跳转?
- 哪里的模块是 浅 的——接口的复杂度几乎和实现一样?
- 哪里为了可测试性而抽取了纯函数,但真正的 bug 却藏在它们 如何被调用 之中(缺乏 局部性)?
- 哪里紧耦合的模块跨越各自的接缝发生泄漏?
- 代码库的哪些部分未被测试,或难以通过其当前接口进行测试?
对任何你怀疑是浅的东西,施加 删除测试:删掉它会让复杂度 集中,还是仅仅把它 挪走?一个"会集中"的"是",正是你想要的信号。
2. 把候选项呈现为一份 HTML 报告
将一个自包含的 HTML 文件写入操作系统的临时目录,这样就不会有东西落进仓库。从 $TMPDIR 解析临时目录,回退到 /tmp(Windows 上为 %TEMP%),并写入 <tmpdir>/architecture-review-<timestamp>.html,使每次运行都得到一个全新文件。为用户打开它——在 macOS 上用 open <path>——并告诉他们绝对路径。
报告使用 通过 CDN 引入的 Tailwind 进行布局和样式设计,并在图/流程/时序能可靠传达结构的地方使用 通过 CDN 引入的 Mermaid 绘制图表。把 Mermaid 与手工打造的 CSS/SVG 视觉元素混用——当关系呈图状(调用图、依赖、时序)时用 Mermaid,当你想要更有编排感的东西(体量图、剖面图、坍缩动画)时用手工构建的 div/SVG。每个候选项都配一张 前/后对比可视化图。要富有视觉表现力。
对每个候选项,渲染一张卡片,包含:
- Files(文件)——涉及哪些文件/模块
- Problem(问题)——为什么当前架构在制造摩擦
- Solution(方案)——用平实的语言描述会改变什么
- Benefits(收益)——用局部性与杠杆的角度来解释,以及测试会如何改善
- Before / After diagram(前/后对比图)——并排、手工绘制,展现浅与加深
- Recommendation strength(推荐强度)——
Strong、Worth exploring、Speculative之一,以徽章形式呈现
在报告末尾放一个 Top recommendation(首推)小节:你会最先着手哪个候选项,以及为什么。
领域方面使用 CONTEXT.md 的词汇,架构方面使用 /codebase-design 的词汇。 如果 CONTEXT.md 定义了 "Order",就谈 "the Order intake module(订单接收模块)"——而不是 "the FooBarHandler",也不是 "the Order service"。
What ships with it
1 file 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 · 72 lines · 56 tokens per session scan A 375f10e40bfa
improve-codebase-architecture is a skill published in the GitHub repository astordu/qoderharness (21 stars, last pushed 7d ago), licensed MIT. It adds 56 tokens to every session and 1,755 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.