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 skills add asherzj/ashers-agent-skills --skill improve-codebase-architecturegit clone --depth 1 https://github.com/asherzj/ashers-agent-skillsWrote 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.
[](https://agentmods.dev/skills/asherzj/ashers-agent-skills/improve-codebase-architecture)<a href="https://agentmods.dev/skills/asherzj/ashers-agent-skills/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/asherzj/ashers-agent-skills/improve-codebase-architecture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/asherzj/ashers-agent-skills/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/asherzj/ashers-agent-skills/improve-codebase-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.01780 |
| Opus 5.5 | $0.00018 | $0.00712 |
| Sonnet 5.5 | $0.00009 | $0.00356 |
| Haiku 4.5 | $0.00004 | $0.00178 |
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 1mo 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
改进代码库架构
呈现架构摩擦,提出深化机会:把浅模块变成深模块(deep module)的重构。目标是可测试性与 AI 可导航性。
本命令以项目的领域模型(domain model)为_依据_,并建立在一套共享的设计词汇之上:
- 调用 Skill 工具并传入 "codebase-design",获取架构词汇表(模块(module)、接口(interface)、深度(depth)、接缝(seam)、适配器(adapter)、杠杆(leverage)、局部性(locality))及其原则(删除测试(deletion test)、「接口即测试面」、「一个适配器 = 假想接缝,两个 = 真实接缝」)。在每条建议中精确使用这些术语,不要漂移到 "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(架构决策记录)记录了本命令不应重新翻案的决策。
流程
1. 探索
**扫描前先定范围:YAGNI。**深化一个模块的回报在于让未来对它的变更更容易,因此要格外看重代码库中最近变更过的部分。在看之前,先决定看哪里,并写下本轮不可扩大的业务范围和必须保持的外部行为:
- 如果用户指定了方向(某个模块、某个子系统、某个痛点),直接采纳,并跳过下面的推断。
- 否则,回溯相当长的一段提交历史(
git log --oneline),找出代码库的热点——反复出现的文件和区域——让这些路径最先吸引你的注意。如果变更分散、没有明确热点,就扩大撒网范围。
先读项目的领域词汇表(CONTEXT.md)以及你将触及区域内的所有 ADR。
然后生成一个子代理去走查代码库。不要遵循僵化的启发式规则;自然地探索,并记下你遇到摩擦的地方:
- 哪里理解一个概念需要在许多小模块之间来回跳转?
- 哪里的模块很浅,接口几乎和实现一样复杂?
- 哪里只是为了可测试性抽出了纯函数,而真正的 bug 藏在它们的调用方式里(没有局部性)?
- 哪里有紧耦合模块跨接缝泄漏?
- 代码库哪些部分没有测试,或者难以通过当前接口进行测试?
- 哪里存在已经达到删除条件的兼容层、旧接口或双轨实现?
对任何你怀疑很浅的东西应用删除测试:删掉它会让复杂度集中,还是只是挪个地方?「会集中」才是你想要的信号。
2. 以 HTML 报告呈现候选
把一个自包含的 HTML 文件写入操作系统临时目录,这样仓库里不会落下任何东西。从 $TMPDIR 解析临时目录,回退到 /tmp(Windows 上是 %TEMP%),写入 <tmpdir>/architecture-review-<timestamp>.html,让每次运行都得到一个新文件。替用户打开它(Linux 用 xdg-open <path>,macOS 用 open <path>,Windows 用 start <path>),并告知绝对路径。
报告用 Tailwind(经 CDN 引入) 做布局和样式,用 Mermaid(经 CDN 引入) 画图——当图/流程/时序能可靠传达结构时使用。把 Mermaid 与手工打造的 CSS/SVG 视觉混用:关系呈图状时(调用图、依赖、时序)用 Mermaid,想要更具编辑感的效果时(体量图、剖面图、折叠动画)用手工构建的 div/SVG。每个候选配一幅前/后可视化对比。要有视觉表现力。
为每个候选渲染一张卡片,包含:
- 文件:涉及哪些文件/模块
- 问题:当前架构为何造成摩擦
- 方案:用平实的语言描述将改变什么
- 收益:从局部性和杠杆的角度解释,以及测试将如何改善
- 删除物:完成后哪些接口、适配层、重复规则或旧测试应当消失
- 范围检查:它是否严格保持现有产品承诺;若需要扩大范围则标记为不适合本轮架构维护
- 前/后图:并排、亲手绘制,呈现「浅」与「深化」
- 推荐强度:
Strong、Worth exploring、Speculative三者之一,渲染为徽章
报告以首选推荐部分收尾:你会先处理哪个候选、为什么。
**领域用 CONTEXT.md 的词汇,架构用 /codebase-design 的词汇。**如果 CONTEXT.md 定义了 "Order",就谈「Order 接入模块」,而不是「FooBarHandler」,也不是「Order 服务」。
ADR 冲突:如果某个候选与现有 ADR 相矛盾,只有当摩擦真实到值得重审该 ADR 时才呈现它。在卡片中清晰标注(例如一个警告式提示框:「与 ADR-0007 相矛盾,但值得重新开启,因为……」)。不要罗列 ADR 所禁止的每一个理论上的重构。
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.
- 1mo ago First seen · 77 lines · 44 tokens per session scan A e2da7a8cb1e7
improve-codebase-architecture is a skill published in the GitHub repository asherzj/ashers-agent-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,780 once invoked, about $0.0002 per session on Opus 5.5. 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…