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 skills add ngocsangyem/MeowKit --skill improve-codebase-architecturegit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/improve-codebase-architecture)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/improve-codebase-architecture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/improve-codebase-architecture.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00124 | $0.02970 |
| Opus 5 | $0.00062 | $0.01485 |
| Sonnet 5 | $0.00025 | $0.00594 |
| Haiku 4.5 | $0.00012 | $0.00297 |
Grade A, and why
mk: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 8d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mk: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.
This skill owns three things only: structural analysis, dependency mapping, and type-safe patch emission. It owns no rendering. Every visual artifact (before/after diagrams, candidate report, HTML) is produced by mk:preview. The skill emits structured findings; mk:preview draws them.
Architecture vocabulary (use exactly)
Self-contained glossary — every suggestion uses these nouns/verbs and no synonyms.
- module — a unit with an interface and an implementation. Never "component", "service", "unit", "layer", "wrapper".
- interface — the surface a caller depends on. Never "API", "signature".
- depth — implementation complexity hidden behind a small interface. deep = small interface, large implementation. shallow = interface nearly as wide as implementation.
- seam — the line where two modules meet. Never "boundary".
- adapter — a substitutable implementation behind a seam. Rule: one adapter = hypothetical seam, two = real seam.
- leverage — one interface serving N call sites.
- locality — related logic (and its bugs) concentrated in one module, not scattered.
- deletion test — would deleting this module concentrate complexity (good — it was shallow) or merely move it (it was load-bearing)? "Concentrates" is the signal to deepen.
Do not invent terms. If a term is not in this glossary, reach for one that is.
Full definitions, the dependency_category taxonomy (used by the findings schema and Step 6), and the replace-don't-layer testing strategy: see references/deep-module-design.md.
Separation of Concerns (hard boundary)
| Concern | Owner |
|---|---|
| Walk codebase, find friction | this skill (via mk:scout) |
| Map dependencies, apply deletion test | this skill |
| Structured candidate findings (JSON) | this skill → tasks/architecture-review/ |
| Before/after diagrams, HTML report | mk:preview --html --diagram (NOT this skill) |
| Grill the chosen candidate's design | mk:grill |
| Emit the refactor patch | this skill (precise Edit, type-safe) |
| Record domain term / decision | mk:project-context / architect agent (ADR) |
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.
- 8d ago First seen · 221 lines · 124 tokens per session scan A e71382dec3a4
mk:improve-codebase-architecture is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 124 tokens to every session and 2,970 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
coding
Use when five specialized coding agents (linter, perf, refactor, security, test) that enforce quality gates across the development lifecycle. From lint enforcement through performance profiling, refactoring, security auditing, and test coverage. Use when working with coding agents.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.