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/chianw/c31/c31-improve-codebase-architecturenpx skills add ChianW/C31 --skill c31-improve-codebase-architecturegit clone --depth 1 https://github.com/ChianW/C31Wrote 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/chianw/c31/c31-improve-codebase-architecture)<a href="https://agentmods.dev/skills/chianw/c31/c31-improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/chianw/c31/c31-improve-codebase-architecture.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.01092 |
| Opus 5 | $0.00032 | $0.00546 |
| Sonnet 5 | $0.00013 | $0.00218 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
c31-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 5d 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.
What it actually says
Improve Codebase Architecture（C31 改良版）
基于 mattpocock/skills 的 improve-codebase-architecture 微调，两处改动：
改动一：报告必须"说人话"（最高优先级，覆盖 HTML-REPORT.md 的文风规则）
原版的受众是工程师，术语表（module/interface/seam/adapter/locality/leverage）直接使用不解释。本版的受众是项目主人（不一定是工程师）。规则：
- 每个候选必须回答三个大白话问题，顺序固定：
- 这份代码是干嘛的？（一句话，用产品语言而非代码语言——坏例子："provider 层的派生指标聚合"；好例子："回答'这家公司现在贵不贵'"）
- 出过什么事 / 有什么隐患？（有返工实证给返工实证；没有就直说"目前只是看着累，没出过 bug"——不许把推测写成事故）
- 做了之后什么变好？（具体到"以后做 X 只需要 Y"，禁止"更易维护"这类空话）
- 每个候选配一个生活类比（酱汁岗位、四科目活页夹这种）。类比是正文，不是点缀。
- 术语表词汇允许出现，但首次出现必须当场解释（如"seam（两块代码的分界线）"）。能不用就不用。
- 推荐强度徽章照常（Strong / Worth exploring / Speculative），但结论部分必须说清排序依据是"已付过学费"还是"只是摩擦"——前者优先于后者。
- 不凑数：只有有实证（返工史/碰撞史/复杂度数据）的候选才进报告，宁缺毋滥。
- 机制验证门（2026-08-19 教训，最高优先级）：痛点证据只证明"这里疼过"，不证明"这个药治这个疼"。每个候选的解法进报告前，必须写出一句话——"这个好处通过什么机制生效？"——并对着实际代码核实该机制（grep 关键函数/读关键路径/必要时跑一下）。机制不成立的候选当场杀死，不得进报告，哪怕痛点证据再硬。判例：masters.ts 分层（"数据改动省重录"在 llmCacheKey=全文 hash 机制下不成立）与 page.tsx 拆分（4 起事故与文件大小无因果）——两个候选的痛点证据都是真的，药方都是假的。
改动二：报告语言跟随调用语言
- 用户用中文调用 → HTML 报告全文中文（含标题、图注、徽章）
- 用户用英文调用 → 全文英文
- 图表内的模块名/函数名保持代码原文（不翻译标识符）
其余流程不变（照原版执行）
- Explore：先定扫描范围（用户指定方向 > git log 热点），有机探索找摩擦点（浅模块、跨接缝泄漏、locality 缺失、难测试处），对疑似浅模块做删除测试
- HTML 报告：自包含单文件，写 OS 临时目录（
architecture-review-<date>-<scope>.html），Tailwind + Mermaid CDN，每候选 before/after 可视化，写完帮用户打开并给出绝对路径。视觉规范照 HTML-REPORT.md（scaffold/图表模式/样式不变——只有文风被上面的"说人话"规则覆盖） - Grilling 环节：用户挑了候选后进入 /grilling，拷问约束、依赖、深化后形状、哪些测试存活；side effects 用 /domain-modeling 就地沉淀
C31 项目惯例补充
- 机械拆分类候选（纯搬运重构）的验收铁律写进报告：测试套件一行不改、全绿；夹带语义修改 = 该票失败
- 报告结论若建议立项，直接附一句"这是 DS 的机械活，可写票据下发"（我们的执行分层：票据 → DeepSeek 施工 → 审计终审）
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.
- 5d ago First seen · 41 lines · 64 tokens per session scan A e2f49cfebc4a
c31-improve-codebase-architecture is a skill published in the GitHub repository ChianW/C31 (1 stars, last pushed 10d ago), licensed MIT. It adds 64 tokens to every session and 1,092 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 2026-08-31.
Other skills, from other repositories
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.
oia-manifest
Emit .harness/oia-manifest.json declaring layer alignment with the OIA v0.1 9-layer reference architecture. Self-describes the harness's MCP wiring, witness signing, audit log, identity posture (always 'none' at v0.1). --check verifies an existing manifest, --dry-run prints without writing, --json emits to stdout.
create-harness
Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a…
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
example-harness
Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming…
repo-genome
7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.