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 bugrabilge/bilge-development-kit --skill refactoring-patternsgit clone --depth 1 https://github.com/bugrabilge/bilge-development-kitWrote 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/bugrabilge/bilge-development-kit/refactoring-patterns)<a href="https://agentmods.dev/skills/bugrabilge/bilge-development-kit/refactoring-patterns"><img src="https://agentmods.dev/badge/skills/bugrabilge/bilge-development-kit/refactoring-patterns/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/bugrabilge/bilge-development-kit/refactoring-patterns"><img src="https://agentmods.dev/badge/skills/bugrabilge/bilge-development-kit/refactoring-patterns.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 | $0.00044 | $0.01954 |
| Opus 5 | $0.00022 | $0.00977 |
| Sonnet 5 | $0.00009 | $0.00391 |
| Haiku 4.5 | $0.00004 | $0.00195 |
Grade A, and why
refactoring-patterns 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 5d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring Patterns
"Refactoring is the art of improving code without changing what it does -- small, safe, relentless steps."
When to Use
- Improving readability or maintainability of existing code
- Reducing code duplication across a codebase
- Preparing code for new features by cleaning up the existing structure
- Planning incremental migrations from legacy to modern architecture
- Reducing technical debt methodically
- Reviewing code that has grown complex or tangled
Foundational Principles
The Refactoring Mindset
- Never refactor and add features in the same commit
- Each refactoring step must keep all tests passing (green-to-green)
- Make the change easy, then make the easy change
- Refactor code you are about to modify; do not refactor unrelated code opportunistically
- If you cannot explain the improvement in one sentence, the refactoring is too large
Safety Net Requirements
- Automated tests covering the code being refactored (minimum: key paths)
- Version control with small, frequent commits (one refactoring step per commit)
- CI pipeline that runs tests on every push
- If tests do not exist, write characterization tests first (tests that document current behavior)
Method-Level Refactorings
Extract Method
- When: A code block inside a function does one identifiable subtask
- How: Move the block to a new function with a descriptive name, pass required variables as parameters
- Goal: Each function reads like a paragraph; the name tells what, the body tells how
- Signal: Comments explaining "what the next block does" -- replace the comment with a function name
Inline Method
- When: A method body is as clear as its name, or the method is a trivial wrapper
- How: Replace calls with the method body; remove the method
- Signal: Method name adds no abstraction value over the code itself
Replace Temp with Query
- When: A temporary variable holds a computed value used once
- How: Extract the computation into a method; call the method directly
- Benefit: Makes the computation reusable and testable independently
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.
- 5d ago First seen · 191 lines · 44 tokens per session scan A 7e6963df4063
refactoring-patterns is a skill published in the GitHub repository bugrabilge/bilge-development-kit (10 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 1,954 once invoked, about $0.0002 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…