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.
npx skills add adriangrantdotorg/Raycast-Skill --skill raycastgit clone --depth 1 https://github.com/adriangrantdotorg/Raycast-SkillWrote 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/adriangrantdotorg/raycast-skill/raycast)<a href="https://agentmods.dev/skills/adriangrantdotorg/raycast-skill/raycast"><img src="https://agentmods.dev/badge/skills/adriangrantdotorg/raycast-skill/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.
<a href="https://agentmods.dev/skills/adriangrantdotorg/raycast-skill/raycast"><img src="https://agentmods.dev/badge/skills/adriangrantdotorg/raycast-skill/raycast.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 | $0.00197 | $0.09963 |
| Opus 5.5 | $0.00079 | $0.03985 |
| Sonnet 5.5 | $0.00039 | $0.01993 |
| Haiku 4.5 | $0.00020 | $0.00996 |
Grade A, and why
raycast scanned grade A with 2 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
*Trigger:* you are about to write a Raycast prop, option, manifest key, or metadata key you have not checked in this session. *Discrimination:* the rules below are enough for workflow decisions; they are not enough for e Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **AppleScript & Keyboard Maestro**: prefer `runAppleScript` from `@raycast/utils`, passing values as an `args` array instead of splicing them into the script text (no quoting bugs). The script reads them with `on run a How it starts
The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Raycast Development
This skill defines the preferred workflow and best practices for building, modifying, and troubleshooting Raycast Extensions (React/Node) and Script Commands (shell scripts with @raycast.* metadata).
0. Reference files — read the one that matches the task
The sections below are the rules. The exact signatures and doc facts live in references/, distilled 09-24-26 from developers.raycast.com and manual.raycast.com (API 2.5.0, @raycast/utils 2.3.0):
| 📄 File | Open it when you are… |
|---|---|
references/platform.md |
editing package.json (commands, modes, interval, arguments, preferences, platforms), using LaunchProps / background refresh / deeplinks, running ray CLI commands, debugging, building AI tools / ai.yaml / evals |
references/api-reference.md |
writing UI or calling @raycast/api: List, Grid, Form, Detail, Actions, MenuBarExtra, Toast/HUD/Alert, Clipboard, Cache, LocalStorage, Keyboard shortcuts, launchCommand, OAuth, AI.ask, WindowManagement, BrowserExtension |
references/utils-hooks.md |
picking or configuring a @raycast/utils hook (usePromise, useCachedPromise, useFetch, useExec, useSQL, useForm, useFrecencySorting…), pagination, optimistic mutate, runAppleScript, OAuthService, and changelog / migration / ESM questions |
references/script-commands-and-app.md |
writing a Script Command (every @raycast.* key, arguments, output per mode, exit codes), or using app features: aliases, hotkeys, Hyper Key, quicklinks, Dynamic Placeholders, raycast:// URLs, MCP, Raycast AI skills, logs |
Trigger: you are about to write a Raycast prop, option, manifest key, or metadata key you have not checked in this session. Discrimination: the rules below are enough for workflow decisions; they are not enough for exact names and defaults (filtering, keepPreviousData, refreshTime…), which drift between API versions. Action: grep the matching reference file first. If it is missing or looks stale, ask the live docs: curl -s 'https://developers.raycast.com/readme.md?ask=<question>' (the answer comes back with excerpts), or grep https://developers.raycast.com/llms-full.txt (two parts, the second at /llms-full.txt/1) and https://manual.raycast.com/llms-full.txt. Then add what you learned to the reference file.
What ships with it
4 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.
- 1mo ago Changed · +294 lines · +138 tokens per session 650bb901bd69
- 1mo ago First seen · 54 lines · 59 tokens per session scan A 949883a6dfa0
raycast is a skill published in the GitHub repository adriangrantdotorg/Raycast-Skill (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 197 tokens to every session and 9,963 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
raycast
Build Raycast extensions with React and TypeScript, create Script Commands, and troubleshoot URL schemes and extension execution on macOS.
astro
Build content-focused websites with Astro — zero JS by default, islands architecture, multi-framework components, and Markdown/MDX support.
antigravity-design-expert
Core UI/UX engineering skill for building highly interactive, spatial, weightless, and glassmorphism-based web interfaces using GSAP and 3D CSS.
algolia-search
Expert patterns for Algolia search implementation, indexing strategies, React InstantSearch, and relevance tuning.
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.
moai-ref-react-patterns
React/Next.js component design patterns, state management strategies, and project structure reference for frontend development. Agent-extending skill that amplifies frontend domain work (spawned via Agent(general-purpose) with frontend instructions) with production-grade React patterns. NOT for: backend API design…