Borrowing it
Nothing to install: this file belongs to dominik1001/caldav-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dominik1001/caldav-mcp/main/.agents/skills/ultracite/SKILL.mdgit clone --depth 1 https://github.com/dominik1001/caldav-mcpWrote 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/dominik1001/caldav-mcp/ultracite)<a href="https://agentmods.dev/skills/dominik1001/caldav-mcp/ultracite"><img src="https://agentmods.dev/badge/skills/dominik1001/caldav-mcp/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/skills/dominik1001/caldav-mcp/ultracite"><img src="https://agentmods.dev/badge/skills/dominik1001/caldav-mcp/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 | $0.00179 | $0.02841 |
| Opus 5.5 | $0.00072 | $0.01136 |
| Sonnet 5.5 | $0.00036 | $0.00568 |
| Haiku 4.5 | $0.00018 | $0.00284 |
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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ultracite — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ultracite
Zero-config linting and formatting for JS/TS projects. Supports three linter backends: Oxlint + Oxfmt (recommended), Biome, and ESLint + Prettier + Stylelint.
Detecting Ultracite
Check if ultracite is in package.json dependencies or devDependencies. Detect the active linter by looking for (searching upward from the current directory):
biome.json/biome.jsonc→ Biomeeslint.config.*(.mjs,.js,.cjs,.ts,.mts,.cts) → ESLint (with Prettier for formatting)oxlint.config.ts,oxlint.config.mtsor.oxlintrc.json→ Oxlint (withoxfmt.config.tsoroxfmt.config.mtsfor formatting; init writes the.mtsform in a package that isn't an ES module)
CLI Commands
# Check for issues (read-only)
bunx ultracite check
# Auto-fix issues
bunx ultracite fix
# Diagnose setup problems
bunx ultracite doctor
# Initialize in a new project
bunx ultracite init
Replace bunx with npx, pnpm exec, or yarn depending on the package manager, so the project's installed Ultracite runs (pnpm dlx and yarn dlx download the latest release instead, and Yarn 1 has no dlx). Only init in a project without Ultracite needs a download runner such as pnpm dlx.
check and fix accept optional file paths: bunx ultracite check src/index.ts. Unknown options are passed through to the underlying linter (e.g. bunx ultracite check --max-warnings 0).
Initialization
bunx ultracite init runs an interactive setup. For non-interactive (CI) use, pass flags:
bunx ultracite init \
--pm bun \
--linter biome \
--editors universal \
--agents claude copilot \
--frameworks react next \
--integrations husky lint-staged \
--yes
Flags:
--pm—npm|yarn|pnpm|bun|deno|nub|aube--linter—oxlint(recommended) |biome|eslint--editors—universal(writes.vscode/settings.jsonfor every VS Code-based editor) |vscode|cursor|devin|codebuddy|antigravity|bob|kiro|trae|void|zed--agents— every choice writes the rules toAGENTS.md.universalwrites only that;claude,gemini,aiderandreplitalso add the import, settings or copy that agent needs to read them; IDs likecodex,copilot,cline,ampandcursor-cli(40 agents supported) need nothing more--frameworks—react|next|solid|vue|svelte|qwik|remix|tanstack|angular|astro|nestjs|jest|vitest|cypress|storybook--integrations—husky|lefthook|lint-staged|pre-commit--hooks— Enable auto-fix hooks:claude|codex|copilot|cursor|devin|codebuddy|deepagents|grok--js-plugins— Opt-in Oxlint JS plugins:@shadcn/lint|anti-slop|eslint-plugin-github|eslint-plugin-jsdoc|eslint-plugin-sonarjs|eslint-plugin-tsdoc|oxlint-plugin-react-doctor--type-aware— Enable type-aware linting (ESLint and Biome: extend theirtype-awarepreset; Oxlint: installsoxlint-tsgolintand setstypeAware), and turn onstrictNullChecksin tsconfig files--install-skill— Install the reusable Ultracite skill after setup--skip-install— Skip dependency installation--yes,-y— Take the defaults without prompting (automatic whenCI=trueor there's no terminal); defaults tooxlintwhen--linteris omitted--quiet— Only print warnings and errors
What ships with it
5 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.
- 2d ago First seen · 152 lines · 179 tokens per session scan A 2be3bfba500d
ultracite is a skill published in the GitHub repository dominik1001/caldav-mcp (105 stars, last pushed 2d ago), licensed MIT. It adds 179 tokens to every session and 2,841 once invoked, about $0.0007 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 2026-10-24.
Other skills, from other repositories
mcp-typescript-sdk-upgrade-to-v2
Upgrades TypeScript code from v1 of the MCP TypeScript SDK (@modelcontextprotocol/sdk) to v2 (@modelcontextprotocol/client, /server, /core and the middleware packages): runs the official codemod, then works through what it cannot rewrite. Use whenever a project depends on @modelcontextprotocol/sdk and the user wants…
add-export
Add a new subpath export to the @cyanheads/mcp-ts-core package. Use when creating a new public API surface that consumers import from a dedicated subpath (e.g., @cyanheads/mcp-ts-core/newutil).
basic-inline-skill
A minimal instruction-only skill with inline content and the function builder alternative.
typescript-lsp
Search TypeScript SYMBOLS (functions, types, classes) - NOT text. Use Glob to find files, Grep for text search, LSP for symbol search. Provides type-aware results that understand imports, exports, and relationships.
typescript-best-practices
A guide to setting up TypeScript projects and writing code that catches more mistakes through type checking. TypeScript is JavaScript with optional checks for the kinds of values code uses.
typescript-best-practices
TypeScript/Node.js best practices. Use when writing or reviewing TypeScript code. Covers type safety, async patterns, and error handling.