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 bahayonghang/my-ai-cli-toolkit --skill code-refactorgit clone --depth 1 https://github.com/bahayonghang/my-ai-cli-toolkitWrote 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/bahayonghang/my-ai-cli-toolkit/code-refactor)<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/code-refactor"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/code-refactor/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/bahayonghang/my-ai-cli-toolkit/code-refactor"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/code-refactor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 28 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00110 | $0.01959 |
| Opus 5.5 | $0.00044 | $0.00784 |
| Sonnet 5.5 | $0.00022 | $0.00392 |
| Haiku 4.5 | $0.00011 | $0.00196 |
Grade A, and why
code-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 12d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Refactor
Refactor existing code without changing behavior. The skill's job is to make code easier to understand, modify, and test while keeping the observable contract stable.
Refactoring is not a license for broad cleanup. Treat every edit as a behavior-preserving transformation with evidence, a bounded target, and verification.
Default Behavior
Choose the mode from the user's scope.
- Broad request: If the user says things like "refactor this module", "clean up this project", or "optimize the code structure", inspect first, propose safe refactor slices, and wait for user approval before broad edits.
- Narrow request: If the user names a file, function, duplicated block, dead symbol, or specific cleanup, directly implement the smallest safe slice and verify it.
- Review-only request: If the user asks for an independent diff or PR review (functional regressions, concurrency, test gaps) without asking to edit, use
code-auditor. If the user asks for code quality review or maintainability findings without asking to edit, usecode-quality-review. - Architecture/RFC request: If the user wants deep-module design, module-boundary candidates, or an architecture RFC rather than a behavior-preserving refactor, treat that as a separate design effort and surface it instead of refactoring in place.
Refactor Types
Classify the requested work before editing. A task may include more than one type, but execute one coherent slice at a time.
| Type | Use when | Good outcome |
|---|---|---|
| Module split | A file or subsystem mixes unrelated responsibilities | Files align with functional modules, ownership, and test boundaries |
| Function/method extraction | One function has multiple small behaviors or hidden phases | Public API stays small; private helpers name meaningful substeps |
| Duplicate consolidation | Similar logic appears repeatedly and may drift | A shared helper removes real duplication without adding thin indirection |
| Naming cleanup | Names hide intent, encode stale details, or force readers to inspect implementation | Names are concise, intention-revealing, and consistent with local style |
| Comment cleanup | Comments repeat code, miss invariants, or hide key assumptions | Comments explain why, contracts, edge cases, and non-obvious decisions |
| Dead-code removal | Code appears uncalled, stale, or orphaned | Removal is backed by call-site, export, framework, and verification checks |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago Changed · +13 tokens per session 4286aeb39b3a
- 1mo ago First seen · 174 lines · 97 tokens per session scan A ea94a9d34864
code-refactor is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (17 stars, last pushed 5d ago), licensed MIT. It adds 110 tokens to every session and 1,959 once invoked, about $0.0004 per session on Opus 5.5. 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
absolute-simplify
Use when the user wants to simplify, clean up, refactor, tidy, or refine code — their staged/unstaged git changes or a target file/path. Reduces complexity, flattens nesting, removes redundancy and dead code, scores each change by value (holding low-value churn), then runs tests to prove nothing broke. Invoke on…
arch-optimize
A software architecture review workflow that scans a codebase for structural risks and measures code quality. It checks issues such as overly complex code, repeated knowledge, changes spreading across many files, circular dependencies, and distorted domain models.
code-simplification
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
refactoring
Improve code structure without changing behavior using proven refactoring patterns. Use when cleaning up code, reducing duplication, improving readability, or restructuring modules.
refactoring-patterns
Apply safe refactoring patterns to improve code structure without changing behavior. Use when cleaning up code, reducing technical debt, or improving maintainability.
software-code-refactoring
Improve production code quality while preserving all existing test behavior. Commonly used for the Refactor phase of TDD red-green-refactor, but applicable to any codebase with tests. Use when production code works but needs cleanup — reducing duplication, improving naming, simplifying complexity, aligning with…