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/voidtechnology/voidtech-claude-plugins/architecture-reviewnpx skills add VoidTechnology/voidtech-claude-plugins --skill architecture-reviewgit clone --depth 1 https://github.com/VoidTechnology/voidtech-claude-pluginsWhat 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 | $0.00039 | $0.01559 |
| Opus 5 | $0.00019 | $0.00779 |
| Sonnet 5 | $0.00008 | $0.00312 |
| Haiku 4.5 | $0.00004 | $0.00156 |
Grade A, and why
architecture-review 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 yesterday.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vendored from mattpocock/skills · MIT © 2026 Matt Pocock · upstream 6eeb81b · 已汉化并完成 VoidTech 插件内自包含适配。LICENSE 见 ../_vendor-licenses/mattpocock-LICENSE
改进代码库架构
找出理解、修改和测试代码时遇到的架构阻力，并提出模块深化方案（deepening）：把职责零散的浅模块整合成接口简单、内部能力完整的深模块。目标是提升可测试性，让开发者和 AI 更容易理解代码。
审查时使用项目现有的功能上下文和统一的架构术语：
- 运行
voidtech-engineering:codebase-design技能，了解架构词汇（module、interface、depth、seam、adapter、leverage、locality）及其原则（移除模块检验、“接口就是测试面”、“一个 adapter 通常不足以证明需要 seam，两个 adapter 才能证明替换需求真实存在”）。每条建议都使用这些术语，不要换成含义不完全相同的 "component"、"service"、"API" 或 "boundary"。 CONTEXT.md中的业务词汇为好的 seam 命名；docs/adr/中的 ADR 记录了本命令不应重新争论的决策。
流程
1. 探查
先阅读项目的业务词汇表（CONTEXT.md）以及你所触及区域内的任何 ADR。
然后用 Agent 工具配 subagent_type=Explore 走查代码库。若当前环境没有 Agent 工具，直接使用文件搜索、符号搜索和测试入口完成同样的探查，不得因此要求安装上游工具。根据实际代码寻找以下问题：
- 在哪里理解一个概念需要在许多小模块之间来回跳？
- 哪里的模块是shallow（浅的）——接口几乎和实现一样复杂？
- 哪里的纯函数仅仅为了可测试性而被抽出，但真正的 bug 藏在它们如何被调用之中（缺乏 locality）？
- 哪些紧耦合模块把内部细节泄漏到了 seam 之外？
- 代码库的哪些部分未被测试，或者通过当前接口难以测试？
对任何疑似浅模块应用移除模块检验：假设删掉它，复杂度是消失了，还是被迫散落到调用方？如果复杂度会散落，说明这个模块可能值得保留并进一步深化。
2. 把候选项呈现为 HTML 报告
把一个自包含的 HTML 文件写到操作系统的临时目录，这样不会有任何东西落进仓库。从 $TMPDIR 解析临时目录，回退到 /tmp（Windows 上为 %TEMP%），并写到 <tmpdir>/architecture-review-<timestamp>.html，让每次运行都得到一个新文件。为用户打开它——Linux 上用 xdg-open <path>，macOS 上用 open <path>，Windows 上用 start <path>——并告诉他们绝对路径。
报告必须离线可读：把全部样式写进 <style>，图表使用语义化 HTML、CSS Grid/Flex 与内联 SVG，不加载 CDN、字体、脚本或其他远程资源。把仓库名、路径、符号名、注释和其他动态文本按 HTML 文本或属性上下文正确转义，绝不把仓库内容拼成标签或 SVG 标记。每个候选项都配一张 before/after 可视化；当关系是图状时用内联 SVG 的方框、连线和箭头表达。
为每个候选项渲染一张卡片，包含：
- Files（文件） — 涉及哪些文件或模块
- Problem（问题） — 当前架构为什么难以理解、修改或测试
- Solution（方案） — 用简单英语描述具体改动
- Benefits（收益） — 使用 locality 和 leverage 解释收益，并说明测试如何改善
- Before / After diagram（改动前后图） — 并排展示模块深化前后的结构
- Recommendation strength（推荐程度） —
Strong、Worth exploring、Speculative之一，以徽标显示
报告以 Top recommendation（首选建议） 段落收尾：说明应优先处理哪个候选项以及原因。
业务命名用 CONTEXT.md 词汇，架构说明用 voidtech-engineering:codebase-design 词汇。 如果 CONTEXT.md 定义了 "Order"，就谈 "the Order intake module"——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.
- yesterday First seen · 68 lines · 39 tokens per session scan A 863cdd31decc
architecture-review is a skill published in the GitHub repository VoidTechnology/voidtech-claude-plugins (2 stars, last pushed 28d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,559 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…