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 alphacornutum/layercake --skill refactorgit clone --depth 1 https://github.com/alphacornutum/layercakeWrote 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/alphacornutum/layercake/refactor)<a href="https://agentmods.dev/skills/alphacornutum/layercake/refactor"><img src="https://agentmods.dev/badge/skills/alphacornutum/layercake/refactor/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/alphacornutum/layercake/refactor"><img src="https://agentmods.dev/badge/skills/alphacornutum/layercake/refactor.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 | $0.00108 | $0.00405 |
| Opus 5.5 | $0.00043 | $0.00162 |
| Sonnet 5.5 | $0.00022 | $0.00081 |
| Haiku 4.5 | $0.00011 | $0.00040 |
Grade A, and why
refactor 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 20d 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
Refactor
Safely restructure code while preserving existing behavior.
Steps
- Verify tests exist — Before touching anything, confirm test coverage on the code you'll change. If tests are missing, write them first against current behavior.
- Name the problem — What exactly is wrong?
- Duplicated logic? Function doing too many things? Poor naming? Tangled dependencies? Wrong abstraction?
- Plan the change — Describe what you'll do before doing it. Small, safe steps.
- One change at a time — Each step keeps the code working. Big rewrites collapse on themselves; small steps stay reversible.
- Run tests after each step — If tests fail, you changed behavior. Undo and try smaller.
- Stop when good enough — Clear, tested, easy to change = done.
Gotchas
- Extract abstractions only when there is real duplication — three similar lines beat a premature helper.
- Reach for a design pattern when the problem calls for one, not to demonstrate knowledge.
- Confirm with the user before renaming across the entire codebase — the blast radius is bigger than it looks.
- Map the downstream callers before touching a public API.
- Keep refactors and feature work in separate commits or PRs.
- Leave code alone when it works, is clear, and is tested — personal preference is not a reason to refactor.
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.
- 20d ago First seen · 28 lines · 108 tokens per session scan A 1524faa347a3
refactor is a skill published in the GitHub repository alphacornutum/layercake (0 stars, last pushed 3d ago), licensed MIT. It adds 108 tokens to every session and 405 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
ae-setup
Diagnose and repair the connection between the AE MCP tools and After Effects — panel not installed, AE not running, Adobe debug preference off, bridge not responding, bridge on the wrong port, CEP refusing the panel's signature. Load when an After Effects tool reports it cannot reach AE, or when the user is setting…
after-effects-scripting
Drive a running After Effects instance directly from the shell to build, edit and render motion graphics — no MCP, plugin or panel required. Use whenever the user wants Claude to work inside After Effects: building animations, title sequences, logo stings, UI/product motion, data visualisations, or fixing an existing…
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.