Improve Codebase Architecture Skill 安全审计

11    <meta charset="utf-8" />12    <title>Architecture review for {{repo name}}</title>13    <script src="https://cdn.tailwindcss.com"></script>14    <script type="module">15      import mermaid from "https://cdn.jsdelivr.net/npm/mermaid@11/dist/mermaid.esm.min.mjs";16      mermaid.initialize({ startOnLoad: true, theme: "neutral", securityLevel: "loose" });17    </script>18    <style>

9596- Lean editorial, not corporate-dashboard. Generous whitespace. Serif optional for headings (`font-serif` works well with stone/slate).97- Colour sparingly: one accent (emerald or indigo) plus red for leakage and amber for warnings.98- Keep diagrams ~320px tall so before/after sits comfortably side by side without scrolling.99- Use `text-xs uppercase tracking-wider` for module labels inside diagrams, so they read as schematic, not as UI.100- The only scripts are the Tailwind CDN and the Mermaid ESM import. The report is otherwise static: no app code, no interactivity beyond Mermaid's own rendering.101

99- Use `text-xs uppercase tracking-wider` for module labels inside diagrams, so they read as schematic, not as UI.100- The only scripts are the Tailwind CDN and the Mermaid ESM import. The report is otherwise static: no app code, no interactivity beyond Mermaid's own rendering.101

5960Do NOT propose interfaces yet. After the file is written, ask the user: "Which of these would you like to explore?"6162### 3. Grilling loop6364Once the user picks a candidate, call the Skill tool with "grilling" to walk the decision tree with them: constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.65

6566Side effects happen inline as decisions crystallize; call the Skill tool with "domain-modeling" to keep the domain model current as you go:6768- **Naming a deepened module after a concept not in `CONTEXT.md`?** Add the term to `CONTEXT.md`. Create the file lazily if it doesn't exist.69- **Sharpening a fuzzy term during the conversation?** Update `CONTEXT.md` right there.70- **User rejects the candidate with a load-bearing reason?** Offer an ADR, framed as: _"Want me to record this as an ADR so future architecture reviews don't re-suggest it?"_ Only offer when the reason would actually be needed by a future explorer to avoid re-suggesting the same thing; skip ephemeral reasons ("not worth it right now") and self-evident ones.71- **Want to explore alternative interfaces for the deepened module?** Call the Skill tool with "codebase-design" and use its design-it-twice parallel sub-agent pattern.

6364Once the user picks a candidate, call the Skill tool with "grilling" to walk the decision tree with them: constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.6566Side effects happen inline as decisions crystallize; call the Skill tool with "domain-modeling" to keep the domain model current as you go:6768- **Naming a deepened module after a concept not in `CONTEXT.md`?** Add the term to `CONTEXT.md`. Create the file lazily if it doesn't exist.69- **Sharpening a fuzzy term during the conversation?** Update `CONTEXT.md` right there.70- **User rejects the candidate with a load-bearing reason?** Offer an ADR, framed as: _"Want me to record this as an ADR so future architecture reviews don't re-suggest it?"_ Only offer when the reason would actually be needed by a future explorer to avoid re-suggesting the same thing; skip ephemeral reasons ("not worth it right now") and self-evident ones.71- **Want to explore alternative interfaces for the deepened module?** Call the Skill tool with "codebase-design" and use its design-it-twice parallel sub-agent pattern.

5354**Use CONTEXT.md vocabulary for the domain, and the `/codebase-design` vocabulary for the architecture.** If `CONTEXT.md` defines "Order," talk about "the Order intake module," not "the FooBarHandler," and not "the Order service."5556**ADR conflicts**: if a candidate contradicts an existing ADR, only surface it when the friction is real enough to warrant revisiting the ADR. Mark it clearly in the card (e.g. a warning callout: _"contradicts ADR-0007, but worth reopening because…"_). Don't list every theoretical refactor an ADR forbids.57