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/ag0os/rails-dev-plugin/refactoring-guidancenpx skills add ag0os/rails-dev-plugin --skill refactoring-guidancegit clone --depth 1 https://github.com/ag0os/rails-dev-pluginWrote 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/ag0os/rails-dev-plugin/refactoring-guidance)<a href="https://agentmods.dev/skills/ag0os/rails-dev-plugin/refactoring-guidance"><img src="https://agentmods.dev/badge/skills/ag0os/rails-dev-plugin/refactoring-guidance.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 | $0.00057 | $0.00759 |
| Opus 5 | $0.00028 | $0.00380 |
| Sonnet 5 | $0.00011 | $0.00152 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
refactoring-guidance 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 4d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring Guidance
You know Fowler's catalog and standard code smells. These directives correct where that knowledge is most often misapplied during code generation.
Scope: Fix What You Were Asked to Fix
- Refactor only the targeted code. Resist "while I'm here" on surrounding code.
- If you spot other smells, note them — don't fix them in the same change.
- A refactoring PR that touches one smell is reviewable. One that touches five is not.
Prioritize by Impact, Not by Textbook Severity
Not all smells deserve fixing. Rank by real-world cost:
- Fix now: Code that causes bugs across the team, blocks feature work, or sits in a file that appears in >30% of recent commits.
- Fix soon: Duplication across 3+ call sites, functions that require 20+ lines of test setup, logic scattered across 4+ files for one concept.
- Leave alone: One-off long parameter lists, single naming nitpicks, style inconsistencies in stable code nobody edits.
A working codebase the team understands beats a theoretically perfect one.
Default Simple, Escalate With Evidence
Apply the simplest pattern that resolves the smell. Escalate only when specific criteria are met:
- Extract function is the default. Escalate to a method object or dedicated class only when: 4+ interacting local variables, would need 3+ params passed between extracted pieces, or the logic warrants its own test suite.
- Keep logic inline is the default. Extract to a separate module/class only when: 2+ call sites need it, it has its own state, or it's independently testable and worth testing alone.
- A simple conditional is fine. Escalate to polymorphism or pattern matching only when the same type/status dispatch appears in 3+ places.
If you can't articulate why the heavier pattern is necessary, use the lighter one.
Moving Code Is Not Simplifying Code
- Extracting to a new file doesn't reduce complexity — it just relocates it. The result must be simpler to understand, not just shorter in each file.
- A shared abstraction with one call site is premature. Inline it.
- Wrapping a function in a class without adding state or encapsulation is ceremony, not design.
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.
- 4d ago First seen · 63 lines · 57 tokens per session scan A d4af8b9f3d26
refactoring-guidance is a skill published in the GitHub repository ag0os/rails-dev-plugin (5 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 759 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…