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/macintog/codex-spine/improve-codebase-architecturenpx skills add macintog/codex-spine --skill improve-codebase-architecturegit clone --depth 1 https://github.com/macintog/codex-spineWhat 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 | $0.00076 | $0.01201 |
| Opus 5 | $0.00038 | $0.00600 |
| Sonnet 5 | $0.00015 | $0.00240 |
| Haiku 4.5 | $0.00008 | $0.00120 |
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Codebase Architecture
Adapted for Codex from Matt Pocock's improve-codebase-architecture,
domain-modeling, and codebase-design skill packets, reviewed at commit
885e2ca4d842d139e9aef4e48d366c63cb1b8013.
Use this skill to surface architecture friction and choose focused deepening opportunities: changes that put meaningful behavior behind a smaller, clearer interface. The goal is better locality, better tests, and easier code navigation.
When To Use This Skill
- The user asks to improve architecture, find refactoring opportunities, consolidate modules, or make a codebase easier to test.
- Understanding a concept requires bouncing through many shallow modules.
- Extracted helpers exist mainly for testability, but bugs still live in caller choreography.
- Tightly coupled modules leak details across their seams.
- The repo is hard for agents to navigate because important concepts do not line up with code structure.
When Not To Use This Skill
- The task is a narrow bug fix, review, or feature request where architecture is not the blocker.
- A repo-local architecture doc, ADR, or skill already gives a stronger task-specific route.
- The user asked for implementation and the architecture direction is already clear.
Vocabulary
Use these words consistently in architecture suggestions. Full definitions are in LANGUAGE.md.
- Module: anything with an interface and an implementation.
- Interface: everything a caller must know to use the module correctly: types, invariants, ordering, errors, configuration, and performance shape.
- Implementation: the code inside a module.
- Depth: how much useful behavior sits behind an interface.
- Seam: where an interface lives; a place behavior can change without editing in place.
- Adapter: a concrete thing satisfying an interface at a seam.
- Payoff: what callers and maintainers get from depth.
- Locality: how much related behavior can be understood or changed in one place.
What ships with it
5 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 · 89 lines · 76 tokens per session scan A 554e8daf4c61
improve-codebase-architecture is a skill published in the GitHub repository macintog/codex-spine (9 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 1,201 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 2026-08-31.
Other skills, from other repositories
bensz-rmd-rules
规范 AI 开发 R Markdown 分析脚本的行为准则。当用户要求"写 Rmd 分析"、"开发 R 脚本"、"做数据分析"时触发。核心原则：遵循主业与副业分离架构（.R 保留完整数据，.Rmd 应用业务阈值），优先使用用户已有 R 包资源；图表默认按 Nature 级别可读性与出版质量生成；专家级解读兼顾弱背景读者，提供四层框架、指标导读与不常用指标首次解释协议；路径验证确保跨平台兼容性。前提：luckyBase 为硬依赖。.
auto-test-project
当用户明确要求"测试项目"、"运行 auto-test-project"或"进行项目级测试"时使用。对完整项目进行多轮 A 轮批判性测试 + B 轮质量检查，系统化发现、记录、修复问题。⚠️ 不适用：用户只是想优化功能（应直接修改）、只是询问项目问题（应直接回答）、没有明确"测试"意图。.
auto-test-code
当用户明确要求"测试代码"、"运行代码审查"或"进行代码自检"时使用。通过多轮 A 轮批判性代码审查 + B 轮代码质量原则检查，系统化发现、记录、修复程序代码中的问题，并将计划/过程/结果统一沉淀到目标代码根目录的 .bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/auto-test-code/{yyyy-mm-dd-hh-mm}/output/tests/ 隔离工作区。⚠️ 不适用：用户只是想优化功能（应直接修改）、只是询问代码问题（应直接回答）、没有明确"测试代码"意图。.
auto-test-skill
当用户明确要求"测试技能"、"运行 auto-test"或"进行批判性测试"时使用。通过多轮 A 轮批判性测试 + B 轮质量原则检查，系统化发现、记录、修复问题，并沉淀可追溯的 .bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/auto-test-skill/output/plans/ 与 .bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/auto-test-skill/output/tests/ 文档。⚠️ 不适用：用户只是想优化功能（应直接修改）、只是询问技能问题（应直接回答）、没有明确"测试"意图。.
frontend-specialist
前端开发专家。用于前端应用、页面、组件、现有 UI 增量改进、已有页面视觉优化、UI/UX 改造、视觉重设计、响应式布局、表单和输入框视觉一致性、设计系统落地、React/Vue/Next.js/Nuxt、Tailwind、shadcn/ui、Radix、MUI、AntD、仪表盘、SaaS、Landing Page、移动端适配、前端性能优化、浏览器截图检查和去除 AI 味 UI。触发后应把“做好看”转化为可执行设计约束，优先复用项目现有组件与视觉语言，小步实现并尽量通过浏览器或 Playwright 做视觉反馈闭环；当用户要改进当前页面或已有界面时，默认先诊断再做局部优化，而不是从 0 重做。.
git-pr-review
当用户明确要求“review 某个 GitHub PR”“评估某个 pull request 是否值得 merge”“帮我判断这个 PR 怎么处理”时使用。基于用户提供的 GitHub 仓库地址、PR 编号/链接和补充说明，进行只读、证据驱动的 PR 审查：理解 PR 解决的问题、评估方案优劣与局限、默认优先使用内置“好 PR”标准并在必要时联网补充、识别恶意或高风险改动，并输出是否建议 merge 的 Markdown 决策报告。⚠️ 不适用：用户要你直接修改 PR 代码、直接 merge PR、或在本地执行 PR 分支中的不可信代码。.