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/alexgilev/agentic-uiWrote 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/rules/alexgilev/agentic-ui/refactor-component)<a href="https://agentmods.dev/rules/alexgilev/agentic-ui/refactor-component"><img src="https://agentmods.dev/badge/rules/alexgilev/agentic-ui/refactor-component/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/rules/alexgilev/agentic-ui/refactor-component"><img src="https://agentmods.dev/badge/rules/alexgilev/agentic-ui/refactor-component.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 | $0.00024 | $0.00841 |
| Opus 5.5 | $0.00010 | $0.00336 |
| Sonnet 5.5 | $0.00005 | $0.00168 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
refactor-component 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/refactor [ComponentName]
When the user types /refactor [ComponentName], execute the full quality refactoring pipeline on that component.
Setup
- Locate the component at
src/components/[ComponentName]/ - Read
.ai/refactoring.mdfor the 6-pass checklist - Read
.ai/code-quality-rules.mdfor anti-pattern detection and architecture rules
Execution
Run all 6 passes in order. One commit per pass. Never combine passes. Never skip a pass.
Pass 1 — Structural Integrity
- Extract sub-components if any JSX block exceeds 50 lines
- Single responsibility per component
- Props hygiene: remove unused, no drilling past 2 levels, max 7-8 props
- Flatten nested ternaries into named variables
- No
any, no unjustifiedas Type - Types in
.types.ts, constants at top or in.constants.ts
Commit: refactor([ComponentName]): structural cleanup
Pass 2 — Token Fidelity Audit
- Grep all
.cssand.tsxfor hardcoded colors (#, rgb, rgba, hsl) → replace withvar(--) - Grep for raw
pxvalues not invar()→ replace with token - Verify 3-tier aliasing: primitive → semantic → component (no skipped tier)
- Verify dark mode token resolution under
[data-theme="dark"] - Generate token coverage report
Commit: refactor([ComponentName]): token compliance
Pass 3 — Performance & Memoization
React.memo()only on components receiving non-primitive props from parentsuseMemo()/useCallback()only where justified — no over-memoization- Remove duplicate CSS declarations and unused classes
- Single-class specificity only, zero
!important - Verify named exports for tree-shaking
Commit: refactor([ComponentName]): performance
Pass 4 — Accessibility Hardening
- Semantic HTML (
<button>not<div onClick>) - Keyboard: Tab order, Enter/Space, Escape, arrow keys for composites
aria-labelon icon-only controls,aria-livefor dynamic content- Contrast ≥ 4.5:1 normal text, focus ring visible in all themes
- Run
jest-axeon all stories → zero violations
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 · 92 lines · 24 tokens per session scan A 7f6635ae94c5
refactor-component is a cursor rule published in the GitHub repository alexgilev/agentic-ui (26 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 841 once invoked, about $0.0001 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 cursor rules, from other repositories
windsurfrules
Create detailed components with these requirements.
state-management
Use the following stack. Do not introduce or recommend Redux or React Context for shared/global state.
backend
Backend development rules for TT Studio - AI model management backend.
tanstack-start-guide
TanStack Start best practices emphasizing client-first architecture, type safety, and modern React patterns.
new-component
Workflow for creating new React components.
tanstack-react-router_routing
TanStack Router: Routing.