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/minhthang1009/dotclaude/refactornpx skills add MinhThang1009/dotclaude --skill refactorgit clone --depth 1 https://github.com/MinhThang1009/dotclaudeWrote 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/minhthang1009/dotclaude/refactor)<a href="https://agentmods.dev/skills/minhthang1009/dotclaude/refactor"><img src="https://agentmods.dev/badge/skills/minhthang1009/dotclaude/refactor.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 | $0.00025 | $0.01173 |
| Opus 5 | $0.00013 | $0.00587 |
| Sonnet 5 | $0.00005 | $0.00235 |
| Haiku 4.5 | $0.00003 | $0.00117 |
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 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Safe Refactor
Refactor = changing code structure WITHOUT changing behavior. If behavior changes → that is a feature/fix, not a refactor.
Step 1: Pre-flight check
Do NOT start refactoring if any of the following is true:
- Working tree is not clean (uncommitted changes) → suggest committing first.
- Current test suite is failing → suggest fixing tests first.
- No tests exist for the code about to be refactored → suggest writing characterization tests first (tests that capture current behavior, even if that behavior may not be correct).
Ask the user if needed:
- Refactor scope: just 1 file, 1 module, or across the codebase?
- Goal: easier to read? Separate responsibility? Remove duplication? Change pattern?
- Are there public API constraints? (Which functions are exported and MUST NOT have their signatures changed?)
Step 2: Analyze & plan
Read the code, understand what it does. Then:
-
List code smells present:
- Long function/class
- Duplicate code
- Magic numbers, magic strings
- Unclear naming
- High coupling between modules
- Implicit side effects
- Inconsistent error handling
-
Propose a refactor plan as small steps, each step:
- Atomic (independently committable)
- Reversible (easy to roll back)
- Verifiable by tests after each step
Example:
Step 1: Extract function `validateEmail` from `signupUser` Step 2: Rename `data` → `userInput` (4 locations) Step 3: Split type `User` into 2 types: `UserInput` and `UserRecord` Step 4: Replace magic number 86400 with const `SECONDS_PER_DAY` -
Present the plan to the user, ask: "OK with this plan? Do all steps, or only some?"
Step 3: Execute step by step
For EACH step:
- Apply the change (Edit file).
- Run tests immediately after. If tests fail → revert immediately, do not continue.
- Run lint/format if the project has it.
- Brief report: "Step N done, tests pass" or "Step N failed because X, reverted".
- Suggest a commit checkpoint:
refactor: extract validateEmail function.
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 · 117 lines · 25 tokens per session scan A 8168ada29e9e
refactor is a skill published in the GitHub repository MinhThang1009/dotclaude (20 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 1,173 once invoked, about $0.0001 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…