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/aixier/AI_TerminalWrote 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/aixier/ai_terminal/ultracite)<a href="https://agentmods.dev/rules/aixier/ai_terminal/ultracite"><img src="https://agentmods.dev/badge/rules/aixier/ai_terminal/ultracite/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/aixier/ai_terminal/ultracite"><img src="https://agentmods.dev/badge/rules/aixier/ai_terminal/ultracite.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 | $0.00755 | $0.00755 |
| Opus 5.5 | $0.00302 | $0.00302 |
| Sonnet 5.5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
ultracite 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Context
Ultracite enforces strict type safety, accessibility standards, and consistent code quality for JavaScript/TypeScript projects using Biome's lightning-fast formatter and linter.
Key Principles
- Zero configuration required
- Subsecond performance
- Maximum type safety
- AI-friendly code generation
Before Writing Code
- Analyze existing patterns in the codebase
- Consider edge cases and error scenarios
- Follow the rules below strictly
- Validate accessibility requirements
- Avoid code duplication
Rules
Accessibility (a11y)
- Always include a
titleelement for icons unless there's text beside the icon. - Always include a
typeattribute for button elements. - Accompany
onClickwith at least one of:onKeyUp,onKeyDown, oronKeyPress. - Accompany
onMouseOver/onMouseOutwithonFocus/onBlur.
Code Complexity and Quality
- Don't use primitive type aliases or misleading types.
- Don't use the comma operator.
- Use for...of statements instead of Array.forEach.
- Don't initialize variables to undefined.
- Use .flatMap() instead of map().flat() when possible.
React and JSX Best Practices
- Don't import
Reactitself. - Don't define React components inside other components.
- Don't use both
childrenanddangerouslySetInnerHTMLprops on the same element. - Don't insert comments as text nodes.
- Use
<>...</>instead of<Fragment>...</Fragment>.
Function Parameters and Props
- Always use destructured props objects instead of individual parameters in functions.
- Example:
function helloWorld({ prop }: { prop: string })instead offunction helloWorld(param: string). - This applies to all functions, not just React components.
Correctness and Safety
- Don't assign a value to itself.
- Avoid unused imports and variables.
- Don't use await inside loops.
- Don't hardcode sensitive data like API keys and tokens.
- Don't use the TypeScript directive @ts-ignore.
- Make sure the
preconnectattribute is used when using Google Fonts. - Don't use the
deleteoperator.
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 · 94 lines · 755 tokens per session scan A d46c428ebd0c
ultracite is a cursor rule published in the GitHub repository aixier/AI_Terminal (24 stars, last pushed 11mo ago), licensed MIT. It adds 755 tokens to every session, about $0.0030 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
error-handling
Error handling patterns for backend services. Apply when handling errors in handlers or services.
bug-hunter
Incident Responder & Debugger (Trigger with raw logs).
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.