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.
git clone --depth 1 https://github.com/KaelSensei/MagicAIBuilderWrote 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/commands/kaelsensei/magicaibuilder/refactor)<a href="https://agentmods.dev/commands/kaelsensei/magicaibuilder/refactor"><img src="https://agentmods.dev/badge/commands/kaelsensei/magicaibuilder/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/commands/kaelsensei/magicaibuilder/refactor"><img src="https://agentmods.dev/badge/commands/kaelsensei/magicaibuilder/refactor.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 | $0.00000 | $0.00886 |
| Opus 5.5 | $0.00000 | $0.00354 |
| Sonnet 5.5 | $0.00000 | $0.00177 |
| Haiku 4.5 | $0.00000 | $0.00089 |
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 1mo 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor Command – Non-Functional Code Improvements
When /refactor <description> is invoked, immediately execute the following steps.
Step 1: Load Project Context & Follow All Rules
- Assume the project root as the working directory
- Load and strictly follow ALL Cursor rules from
.cursor/rules/*.mdc:security.mdc- Security requirementstechnical-stack.mdc- React Native/SQLite patternsdocumentation.mdc- Documentation update requirementsversion-management.mdc- Git commit/push workflow
- Read relevant documentation:
README.md- Architecture documents
- Any file directly affected by the refactor
- Identify the current Git branch and assume it is a refactor branch, not
main
Step 2: Define Refactor Scope (Critical)
- Parse the description provided after
/refactor - Explicitly define what is allowed:
- Code organization
- Naming
- Readability
- Duplication removal
- Type safety improvements
- Explicitly define what is not allowed:
- No behavior changes
- No logic changes
- No feature additions
- No bug fixes (use
/fixinstead)
- If scope is ambiguous, stop and ask before proceeding
Step 3: Security & Safety Validation
Before making changes:
- Assume refactors can accidentally introduce vulnerabilities
- Review affected code for:
- Hidden logic changes
- Control-flow alterations
- Subtle semantic changes
- Use MCP (Model Context Protocol) or equivalent reasoning to ensure:
- Refactor preserves behavior exactly
- No new execution paths are introduced
- No backdoors, dynamic execution, or unsafe patterns appear
- If exact equivalence cannot be guaranteed, abort and ask
Step 4: Perform the Refactor
- Apply minimal and mechanical transformations only
- Prefer:
- Extracting small pure functions
- Improving naming consistency
- Reducing nesting
- Improving typing and explicitness
- Avoid:
- Reordering logic unless provably equivalent
- Changing conditionals or loops
- Introducing new dependencies
- Keep changes tightly scoped and easily reviewable
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.
- 1mo ago First seen · 132 lines · 0 tokens per session scan A e97c4d2c2e48
refactor is a command published in the GitHub repository KaelSensei/MagicAIBuilder (2 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 886 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
add-endpoint
Scaffold a new API endpoint with full layering.
review
Review code changes against project conventions.
fix-issue
Investigate and fix an issue.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.