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 agentmods add skills/sacredvoid/skillkit/raycast-automatornpx skills add sacredvoid/skillkit --skill raycast-automatorgit clone --depth 1 https://github.com/sacredvoid/skillkitWrote 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/sacredvoid/skillkit/raycast-automator)<a href="https://agentmods.dev/skills/sacredvoid/skillkit/raycast-automator"><img src="https://agentmods.dev/badge/skills/sacredvoid/skillkit/raycast-automator.svg" alt="Measured on agentmods" 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 | $0.00089 | $0.03207 |
| Opus 5 | $0.00044 | $0.01604 |
| Sonnet 5 | $0.00018 | $0.00641 |
| Haiku 4.5 | $0.00009 | $0.00321 |
Grade A, and why
raycast-automator 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 3d 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 — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Raycast Automator
Build Raycast extensions and script commands from natural language task descriptions. Handles the full lifecycle: analysis, code generation, setup, and dev launch.
Output Directory
All output goes to ~/Documents/raycast-scripts/:
- Script commands: files directly in the root (e.g.,
my-script.sh) - Extensions: subdirectories (e.g.,
my-extension/src/index.tsx)
Create the directory if it doesn't exist. For extensions, create the subdirectory named after the extension.
Decision Flow
User describes a task
│
├─ Analyze complexity
│ ├─ Needs rich UI (lists, forms, grids, detail views)? → Extension
│ ├─ Needs OAuth or token management? → Extension
│ ├─ Needs persistent state across runs? → Extension
│ ├─ Needs menu bar presence? → Extension
│ ├─ Needs pagination or streaming data? → Extension
│ ├─ Simple system operation (open, toggle, copy)? → Script Command
│ ├─ Opens URL or does clipboard work? → Script Command
│ ├─ Runs a shell command or API call with simple output? → Script Command
│ └─ 1-3 simple text inputs, no interactive UI? → Script Command
│
├─ Present recommendation with reasoning to user
├─ User confirms or overrides
│
├─ IF Script Command:
│ ├─ Pick language:
│ │ ├─ macOS + simple task → Bash
│ │ ├─ Windows + simple task → Batch/PowerShell
│ │ ├─ Complex logic / API calls → Python
│ │ └─ Mac-native automation → AppleScript
│ ├─ Generate script with full metadata block
│ ├─ chmod +x the file
│ ├─ Ensure ~/Documents/raycast-scripts/ is created
│ └─ Tell user to add script directory in Raycast if first time
│
└─ IF Extension:
├─ Scaffold project structure
├─ Generate package.json with full manifest
├─ Generate src/ entry point(s)
├─ Run npm install
├─ Run npm run dev
└─ Confirm extension appears in Raycast
What ships with it
3 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.
- 3d ago First seen · 360 lines · 89 tokens per session scan A 6540be44f65f
raycast-automator is a skill published in the GitHub repository sacredvoid/skillkit (10 stars, last pushed 5mo ago), licensed MIT. It adds 89 tokens to every session and 3,207 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
ds-deps
Dependency upgrade loop — classify each dependency as safe-patch/safe-minor/review-major, apply safe groups with per-group commits, surface majors with migration notes and rollback. Use when upgrading dependencies or auditing for outdated/vulnerable packages.
ds-rig
Detects the host and harnesses, installs/updates a pinned automation toolset, hardens every tool and harness against telemetry, and applies safe allow/ask/deny permission profiles. Use for setting up or upgrading the AI dev environment, hardening tool privacy, or configuring harness permissions.
Cursor Workflow Optimizer
Master Cursor IDE with optimal configurations, custom rules, MCP integrations, and workflow patterns that 10x developer productivity.
focus-productivity
Use this skill for deep work, managing developer energy and focus, task prioritization, beating procrastination, managing distractions, building sustainable work habits, or structuring a productive development day. Trigger on keywords: productivity, focus, procrastination, distracted, time management, deep work…
image-fetcher
Fetch relevant, high-quality, free-to-use images from the web. Accepts a description/query, or scans the current directory for context. Sources from Unsplash, Pexels, and Pixabay APIs (if keys configured) with a zero-config WebSearch fallback.
happiness-skill
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.