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 commands/onmyway133/claude-code-plugins/refactorgit clone --depth 1 https://github.com/onmyway133/claude-code-pluginsWhat 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 | $0.00000 | $0.00432 |
| Opus 5 | $0.00000 | $0.00216 |
| Sonnet 5 | $0.00000 | $0.00086 |
| Haiku 4.5 | $0.00000 | $0.00043 |
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 2d 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
Analyze code and suggest meaningful refactoring improvements.
Usage
/refactor [file_path] [focus_area]
Arguments:
file_path- File or directory to analyze (required)focus_area- Optional:readability,performance,testability,structure
Refactoring Process
Step 1: Understand Current State
Read the target code and identify:
- What the code does (business logic)
- Current patterns and abstractions
- Dependencies and coupling
- Test coverage (if tests exist)
Step 2: Identify Opportunities
Look for these refactoring candidates:
Structure Issues
- Functions/methods doing too many things
- Deep nesting that obscures logic
- God classes with too many responsibilities
- Scattered related functionality
Readability Issues
- Unclear variable/function names
- Magic numbers or strings
- Complex conditionals that need extraction
- Missing or misleading abstractions
Performance Issues
- Unnecessary allocations in loops
- Redundant computations
- N+1 query patterns
- Blocking operations that could be async
Testability Issues
- Hard dependencies that prevent mocking
- Side effects mixed with pure logic
- Global state usage
- Tightly coupled components
Step 3: Propose Changes
For each suggestion:
## Refactoring: [Name of Change]
**Current Code:**
[Relevant snippet]
**Proposed Change:**
[Refactored code]
**Why This Helps:**
- [Benefit 1]
- [Benefit 2]
**Risk Level:** Low / Medium / High
**Effort:** Small / Medium / Large
Step 4: Prioritize
Rank suggestions by:
- High impact, low risk changes first
- Changes that enable future improvements
- Quick wins before large restructuring
Guidelines
- Preserve existing behavior unless told otherwise
- Small, incremental changes over big rewrites
- Each refactoring should be independently applicable
- Consider backward compatibility
- Suggest tests for risky changes
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.
- 2d ago First seen · 88 lines · 0 tokens per session scan A 786a903ec4ee
refactor is a command published in the GitHub repository onmyway133/claude-code-plugins (5 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 432 tokens. 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 commands, from other repositories
pr
Command "pr" from echoVic/blade-code, covering 当前状态, 变更摘要, 变更文件, pr 目标分支 and 要求.
profile
Save, apply, and share multi-agent configuration profiles.
doctor
Run a system health check to diagnose common issues.
rollback
Restore a skill to its previous version. Requires a history entry — created automatically when you use rolecraft update or re-install over an existing skill.
bundle
Install multiple skills at once from inline sources or a bundle file.
completions
Generate shell completion scripts for bash, zsh, and fish.