A development guide for Raycast extensions, which are small commands and tools that run inside the Raycast launcher for macOS. It covers their project structure, settings, screens, and data-handling helpers.

Use it when building Raycast commands or tools with TypeScript and React, including list, grid, detail, and form interfaces.

It provides the conventions needed to make an extension's commands, interface, loading states, and manifest fit Raycast's expected format.

raycast — Skill for Claude Code by bendrucker/claude

Install

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.

Any agent

npx skills add bendrucker/claude --skill raycast

Clone the repo

git clone --depth 1 https://github.com/bendrucker/claude

Made for: Claude Code.

Or install raycast, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bendrucker/claude/raycast/github.svg)](https://agentmods.dev/skills/bendrucker/claude/raycast)

Your own site

<a href="https://agentmods.dev/skills/bendrucker/claude/raycast"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/raycast/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bendrucker/claude/raycast"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/raycast.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 603 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00027	$0.00603
Opus 5.5	$0.00011	$0.00241
Sonnet 5.5	$0.00005	$0.00121
Haiku 4.5	$0.00003	$0.00060

Measured 2mo ago against content hash 1f899538d330, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

raycast 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 2mo 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.

plugins/raycast/skills/raycast/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Raycast

Project Structure

Commands map by name to src/<name>.tsx. Tools live in src/tools/<name>.ts. Use .tsx for UI commands, .ts for no-view commands and tools. Icons go in assets/. The package.json serves as both the npm manifest and the Raycast extension manifest.

See references/manifest.md

Manifest

The package.json is a superset of npm's format with Raycast-specific fields: commands, tools, preferences, platforms, categories, icon, and author. Command modes are view (renders UI), no-view (runs silently), and menu-bar (menu bar extra).

See references/manifest.md

Components

React-based UI with @raycast/api. Top-level views: List, Grid, Detail, Form. Wrap actions in ActionPanel with Action items. Always pass isLoading to top-level components. Use List.EmptyView for empty states.

See references/components.md

Hooks

@raycast/utils provides data-fetching and state hooks: useFetch for URL fetching, usePromise and useCachedPromise for async functions with stale-while-revalidate caching, useForm for form validation, useLocalStorage for persistent state, and useExec for shell commands. Use keepPreviousData to prevent flickering during search.

See references/hooks.md

AI Tools

Tools export a default async function with a typed Input parameter. JSDoc comments on the Input type teach the AI to use the tool. Export a confirmation function for destructive operations. Configure ai.instructions in package.json for extension-level guidance.

See references/ai-tools.md

Development

Bootstrap with npx create-raycast-extension. Install dependencies with npm install. Run npm run dev for development with hot reloading. Run npm run build to type-check and bundle. Run npm run lint for code style. Use npm (not yarn or pnpm) and commit package-lock.json.

Read the full file on GitHub · 49 lines

Files

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.

Changes

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.

2mo ago First seen · 49 lines · 27 tokens per session scan A 1f899538d330

Subscribe to this mod's changes

raycast is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 603 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 2026-09-03.

Claude Code Frontend Productivity React claude-code-plugin

raycast next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
raycastbendrucker/claude	Skill	18	today	MIT	A	27	Claude Code
recipe-front-reviewshinpr/claude-code-workflows	Skill	713	4d ago	MIT	A	29	Claude Code
typescript-rulesshinpr/claude-code-workflows	Skill	713	4d ago	MIT	A	39	Claude Code
add-teamsmicrosoft/power-platform-skills	Skill	1.1k	today	MIT	A	31	Claude Code
relationsLifecycle-Innovations-Limited/claude-ops	Skill	550	3d ago	MIT	A	27	Claude Code
styleseedbitjaru/styleseed	Skill	1.0k	yesterday	MIT	A	39	Claude Code, Codex
llm-friendly-contextshinpr/claude-code-workflows	Skill	713	4d ago	MIT	A	52	Claude Code