improve-codebase-architecture
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
- License 许可
- MIT
- 所属仓库
- stevesolun/ctx
- 最近更新
- 2026-10-15
- Stars
- ★ 593
- Forks
- 69
01 前言 Front Matter
- name
- improve-codebase-architecture
- description
- Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
02 资源文件 3
- 参考文档DEEPENING.md2.5 KB
- 参考文档INTERFACE-DESIGN.md2.7 KB
- 参考文档LANGUAGE.md3.7 KB
03 SKILL.md 正文
Improve Codebase Architecture
Surface architectural friction and propose deepening opportunities — refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.
Glossary
Use these terms exactly in every suggestion. Consistent language is the point — don't drift into "component," "service," "API," or "boundary." Full definitions in LANGUAGE.md.
- Module — anything with an interface and an implementation (function, class, package, slice).
- Interface — everything a caller must know to use the module: types, invariants, error modes, ordering, config. Not just the type signature.
- Implementation — the code inside.
- Depth — leverage at the interface: a lot of behaviour behind a small interface. Deep = high leverage. Shallow = interface nearly as complex as the implementation.
- Seam — where an interface lives; a place behaviour can be altered without editing in place. (Use this, not "boundary.")
- Adapter — a concrete thing satisfying an interface at a seam.
- Leverage — what callers get from depth.
- Locality — what maintainers get from depth: change, bugs, knowledge concentrated in one place.
Key principles (see LANGUAGE.md for the full list):
- Deletion test: imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it was earning its keep.
- The interface is the test surface.
- One adapter = hypothetical seam. Two adapters = real seam.
This skill is informed by the project's domain model. The domain language gives names to good seams; ADRs record decisions the skill should not re-litigate.
Process
1. Explore
Read the project's domain glossary and any ADRs in the area you're touching first.
Then use the Agent tool with subagent_type=Explore to walk the codebase. Don't follow rigid heuristics — explore organically and note where you experience friction:
- Where does understanding one concept require bouncing between many small modules?
- Where are modules shallow — interface nearly as complex as the implementation?
- Where have pure functions been extracted just for testability, but the real bugs hide in how they're called (no locality)?
- Where do tightly-coupled modules leak across their seams?
- Which parts of the codebase are untested, or hard to test through their current interface?
Apply the deletion test to anything you suspect is shallow: would deleting it concentrate complexity, or just move it? A "yes, concentrates" is the signal you want.
2. Present candidates
Present a numbered list of deepening opportunities. For each candidate:
- Files — which files/modules are involved
- Problem — why the current architecture is causing friction
- Solution — plain English description of what would change
- Benefits — explained in terms of locality and leverage, and also in how tests would improve
Use CONTEXT.md vocabulary for the domain, and LANGUAGE.md vocabulary for the architecture. If CONTEXT.md defines "Order," talk about "the Order intake module" — not "the FooBarHandler," and not "the Order service."
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 (e.g. "contradicts ADR-0007 — but worth reopening because…"). Don't list every theoretical refactor an ADR forbids.
Do NOT propose interfaces yet. Ask the user: "Which of these would you like to explore?"
3. Grilling loop
Once the user picks a candidate, drop into a grilling conversation. Walk the design tree with them — constraints, dependencies, the shape of the deepened module, what sits behind the seam, what tests survive.
Side effects happen inline as decisions crystallize:
- Naming a deepened module after a concept not in
CONTEXT.md? Add the term toCONTEXT.md— same discipline as/grill-with-docs(see CONTEXT-FORMAT.md). Create the file lazily if it doesn't exist. - Sharpening a fuzzy term during the conversation? Update
CONTEXT.mdright there. - 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. See ADR-FORMAT.md.
- Want to explore alternative interfaces for the deepened module? See INTERFACE-DESIGN.md.
04 同仓库更多 Skills
toolbox
Pre/post dev toolbox — named bundles of skills/agents loaded before development work and councils of experts invoked after. Run /toolbox or the toolbox.py CLI to list, activate, initialize, export, import, and validate toolboxes. Invoke at the start or end of a dev session, when setting up a new repo, or when sharing toolboxes with a team.
skill-router
Alive skill router — reads the current project's stack and loads/unloads skills dynamically. Invoke at session start or when project context changes.
repo-stats-autoupdate
Keeps README badge + inline counts in sync with the real number of skills, agents, graph nodes/edges, communities, converted pipelines, and test inventory. Runs automatically on every commit via a git pre-commit hook. Use when the README drifts from reality or before publishing a release.
find-skills
Discover installable agent skills from ctx's shipped Skills.sh catalog, the Skills.sh search API, and the npx skills CLI. Use when a user asks whether a skill exists, wants to add/update a skill, or needs a repeatable procedure for finding candidate skills safely.
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.
zoom-out
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.