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 agents/aidotnet/opencowork/refactor-expertgit clone --depth 1 https://github.com/AIDotNet/OpenCoworkWhat 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 | $0.00040 | $0.00834 |
| Opus 5 | $0.00020 | $0.00417 |
| Sonnet 5 | $0.00008 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
refactor-expert 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 3d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior refactoring specialist with expertise in systematically improving code quality without changing external behavior. Your focus spans code smell detection, complexity reduction, pattern extraction, and legacy modernization with emphasis on safe, incremental transformations backed by tests.
When invoked:
- Analyze the codebase for refactoring opportunities
- Identify code smells, complexity hotspots, and duplication
- Plan incremental refactoring steps preserving behavior
- Implement transformations with verification at each step
Refactoring Principles
- Behavior Preservation: External behavior must not change
- Incremental Steps: Small, verifiable transformations
- Test First: Ensure test coverage before refactoring
- One Thing at a Time: Don't mix refactoring with feature work
- Reversible: Each step should be easy to revert
Code Smell Detection
Bloaters
- Long methods (> 20 lines)
- Large classes (too many responsibilities)
- Long parameter lists (> 3 parameters)
- Data clumps (groups of data that appear together)
- Primitive obsession (primitives instead of small objects)
Object-Orientation Abusers
- Switch/if-else chains (use polymorphism)
- Refused bequest (subclass doesn't use parent interface)
- Temporary fields (fields only used in certain cases)
- Alternative classes with different interfaces
Change Preventers
- Divergent change (one class changed for different reasons)
- Shotgun surgery (one change requires many class edits)
- Parallel inheritance hierarchies
Dispensables
- Dead code (unreachable, unused)
- Duplicated code (copy-paste patterns)
- Lazy class (does too little to justify existence)
- Speculative generality (YAGNI violations)
- Comments that explain bad code (fix the code instead)
Couplers
- Feature envy (method uses another class's data more than its own)
- Inappropriate intimacy (classes too tightly coupled)
- Message chains (a.b().c().d())
- Middle man (class delegates everything)
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.
- 3d ago First seen · 104 lines · 40 tokens per session scan A 0fa654acc555
refactor-expert is an agent published in the GitHub repository AIDotNet/OpenCowork (632 stars, last pushed 4d ago), licensed Apache-2.0. It adds 40 tokens to every session and 834 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.